Next Article in Journal
Statistics and 3D Modelling on Soil Analysis by Using Unmanned Aircraft Systems and Laboratory Data for a Low-Cost Precision Agriculture Approach
Next Article in Special Issue
Automated Mapping of Cropland Boundaries Using Deep Neural Networks
Previous Article in Journal
Robust Coffee Rust Detection Using UAV-Based Aerial RGB Imagery
Previous Article in Special Issue
Comparing Two Methods of Leaf Area Index Estimation for Rice (Oryza sativa L.) Using In-Field Spectroradiometric Measurements and Multispectral Satellite Images
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
AgriEngineering
Volume 5
Issue 3
10.3390/agriengineering5030089
agriengineering-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Mapping Shrimp Pond Dynamics: A Spatiotemporal Study Using Remote Sensing Data and Machine Learning

by
Pavan Kumar Bellam
1,*,
Murali Krishna Gumma
2,*,
Pranay Panjala
1,
Ismail Mohammed
1 and
Aya Suzuki
3
1
Geospatial and Big Data Sciences, International Crops Research Institute for the Semi-Arid Tropics, Hyderabad 502324, India
2
Geospatial and Big Data Sciences, International Crops Research Institute for the Semi-Arid Tropics, Niamey BP 12404, Niger
3
Graduate School of Frontier Sciences, The University of Tokyo, Tokyo 153-8505, Japan
*
Authors to whom correspondence should be addressed.
AgriEngineering 2023, 5(3), 1432-1447; https://doi.org/10.3390/agriengineering5030089
Submission received: 22 June 2023 / Revised: 27 July 2023 / Accepted: 11 August 2023 / Published: 25 August 2023
(This article belongs to the Special Issue Remote Sensing-Based Machine Learning Applications in Agriculture)
Browse Figures
Review Reports Versions Notes

Abstract

:
Shrimp farming and exporting is the main income source for the southern coastal districts of the Mekong Delta. Monitoring these shrimp ponds is helpful in identifying losses incurred due to natural calamities like floods, sources of water pollution by chemicals used in shrimp farming, and changes in the area of cultivation with an increase in demand for shrimp production. Satellite imagery, which is consistent with good spatial resolution and helpful in providing frequent information with temporal imagery, is a better solution for monitoring these shrimp ponds remotely for a larger spatial extent. The shrimp ponds of Cai Doi Vam township, Ca Mau Province, Viet Nam, were mapped using DMC-3 (TripleSat) and Jilin-1 high-resolution satellite imagery for the years 2019 and 2022. The 3 m spatial resolution shrimp pond extent product showed an overall accuracy of 87.5%, with a producer’s accuracy of 90.91% (errors of omission = 11.09%) and a user’s accuracy of 90.91% (errors of commission = 11.09%) for the shrimp pond class. It was noted that 66 ha of shrimp ponds in 2019 were observed to be dry in 2022, and 39 ha of other ponds had been converted into shrimp ponds in 2022. The continuous monitoring of shrimp ponds helps achieve sustainable aquaculture and acts as crucial input for the decision makers for any interventions.

1. Introduction

Over the past 3 decades, aquaculture in Asia has produced more than 90% of the world’s output and played significant roles in food security, poverty alleviation, employment, and overall economic development in many Asian countries. Aquaculture has been a long-standing custom in Asia, although it has only recently emerged, some four or five decades ago, as a major food production industry [1]. Shrimp farming in Viet Nam has been growing discernibly since the government passed a resolution in 2000, allowing the conversion of less-productive rice land in coastal areas to aquaculture ponds [2]. In terms of shrimp exports, Viet Nam placed third in the world in 2019, with 13.6% of the market share, behind only India (15.7%) and Ecuador (14%) [3]. The shrimp production plan by the Ministry of Agriculture and Rural Development in Viet Nam predicted that the shrimp farming area would be 750,000 ha in 2022 and export turnover would be over USD 4 billion, up 2.56% compared to 2021. Aquaculture, including shrimp ponds, is a large contributor to global food security and rural livelihoods and can also help preserve sustainable coastal environments [4,5,6,7,8].
In Viet Nam, the Mekong Delta contains 67% of the country’s total water bodies, including fresh and brackish water bodies other than rivers, whereas the land area is only 12% of the total area [9]. In Ca Mau Province, coastal aquaculture faces a rapid shift, with increasing production and intensive shrimp culture resulting in poor water quality [10].
Various studies in the Mekong Delta focus on sustainable aquaculture development and the combined farming system of agriculture and aquaculture [11,12]. Many sustainable issues concern water quality due to chemical usage in shrimp cultivation [13,14,15,16,17]. Certain studies are related to climate change impacts on agriculture and the aquaculture sector [18]. Despite these many studies based on statistics and farmer interviews, very few EO-based monitoring systems have been developed for shrimp ponds [19], and most studies carried out have been related to changes in mangrove areas [20,21]. Monitoring aquaculture products has shifted to relying heavily on remote sensing technology due to its advantages in estimating the area under cultivation and real-time monitoring of ponds [22,23,24,25,26]. Flood detection, along with wetlands and water bodies identification, play a major role in contributing to aquaculture mapping [27,28]. Many studies have generated and used water-based indices [27,29,30] to identify water bodies with a variety of satellite imagery ranging from moderate (MODIS) to high (Sentinel) spatial resolution [31]. Previously, many aquaculture mapping studies were based on open-source satellite imagery, such as Landsat, and analyses based on Sentinel imagery with more spectral bands but with lower spatial resolution were also carried out [32,33,34,35], in addition to time series analysis [36,37]. Recently, many water bodies and aquaculture mapping studies, particularly on a global scale, have been conducted using a cloud platform, especially Google Earth Engine [38,39,40,41,42,43]. Since the study area is very highly dominated by water bodies that include ponds and major and minor streams, approaches such as segmentation [44] and deep learning-based methodologies alone cannot classify the variations created by newly developing minor ponds [45,46,47]. In order to differentiate water bodies, very high spatial resolution data are needed. This study utilized very-high-resolution data (~3 m) and adopted machine learning algorithms as well as vectorization for classifying variations in water bodies to identify shrimp ponds.
Many Asian nations have not yet fully adopted good aquaculture governance. The rapid growth in the aquaculture sector has given rise to some of the most difficult sustainability problems, including inefficient resource use, detrimental environmental effects, frequent disease outbreaks, and food safety threats, which in turn limit the sector’s potential to grow sustainably in the future. Monitoring shrimp ponds using EO data could be useful in grasping a firm understanding of the current situation of the aquaculture sector to meet the increased demand for aquatic food and sustain aquaculture’s much-needed expansion.
The primary objectives of this research are thus the development of a system for the regional-level mapping of coastal pond aquaculture for the Cai Doi Vam Township, Phu Tan District, Ca Mau Province, based on high spatial resolution single-date satellite imagery and ground truth data, as well as assessment of the accuracy and analysis of aquaculture areas.

2. Data

2.1. Study Area

This study focused on the Cai Doi Vam Township Phu Tan District, a rural district of Ca Mau Province in the southern coastal zone of the Mekong Delta region of Viet Nam (Figure 1), which lies at 8°52′ N and 104°49′ E. The study area is highly vulnerable to natural disasters like floods, droughts, and coastal erosion. The time period under investigation is from 2019 to 2022, during which extensive shoreline erosion was observed in the region. Ca Mau province was particularly affected, with an erosion rate of 32.5 m/year observed in the east and −12.9 m/year in the west after five years. There is a complex climatic context in the study area; according to the Vietnam Meteorological and Hydrological Administration, the region experienced a higher number of typhoons and tropical depressions than in previous years. These weather events were associated with increased rainfall and storm surges, which likely contributed to the observed coastal erosion [48,49].
Vietnam has experienced a warming trend over the past few decades, with an increase in average temperature of 0.5 °C per decade. This warming trend is projected to continue, with potentially significant impacts on the region’s hydrology, including changes in precipitation patterns and sea level rise. The hydrology of the Cai Doi Vam area is complex, with a range of natural factors contributing to coastal erosion. These factors include the tidal regime, flow velocity and direction, wave height and direction to shore, and sediment volume [50,51].
Phu Tan District has a total area of 46,433 ha with all the areas being affected by the saline intrusion, which also applies to the Cai Doi Vam Sub-district [52]. This area is highly dominated by shrimp and other ponds.

2.2. Satellite Data

The detection of small-scale pond aquaculture structures with a size of less than 1 hectare is only achievable with high-resolution imagery. The analysis was carried out based on optical high-resolution geometric (DMC3) sensor imaging with a spatial resolution of 3.2 m from Triplesat on 4 March 2019. Jilin satellite images for 2022 were collected on a different single date and had a comparable spatial resolution (2.88 m of MS).
Pan-sharpening with image data fusion and image enhancements was applied based on linear stretches, and mosaicking was carried out on georeferenced datasets. The three bands were NIR, red, and green color chosen for a composite FCC, as shown in Figure 1. The bands and their spatial characteristics of satellite imagery and the utilization of different satellite imagery in the study are shown in Table 1. Single-date TripleSat and Jilin imagery and temporal Sentinel-2 imagery were used for the study.

2.3. Ground Survey Data

Around 500 sample points related to shrimp cultivation and other LULC were collected across Phu Tan District. Out of the collected samples, 45 sample shrimp pond points were observed within the study area of Cai Doi Vam.
Data was collected during 15–22 October 2022 (Figure 1) using high spatial resolution google earth imagery on the following: (a) Location coordinates; (b) water bodies; (c) fishponds and shrimp ponds; (d) wetlands; and (e) settlements; (f) land cover categories (for example, trees, shrubs, grasses, and hills); (g) Documenting the landscape using, high spatial resolution google earth imagery. The purpose of this exercise was to identify different water body classes accurately during the classification process and assess the accuracy of the final maps.

3. Methods and Approaches

3.1. Wetlands and Land Use Mapping

The land use and land cover with the shrimp class were mapped using DMC3 data for 2019, while the same was mapped using Jilin data for 2022 with the help of unsupervised classification [53,54]. An accuracy assessment was performed with validation data. Spatial analysis was used to create spatial products with a greater resolution of 3 m that recorded changes effectively (Figure 2).
The primarily unsupervised classification was conducted targeting the LULC of the study area and potential shrimp ponds that can be identified. Satellite imagery was classified using ISO CLASS cluster K-means unsupervised classification with a convergence value of 0.99 and 20 iterations, yielding 20 classes followed by successive generalization. These classes were identified using visual interpretation from Google Earth imagery. There is an opportunity to observe temporal changes in the study region using Google Earth imagery. We further used Sentinel 2-based various water indices to create a water bodies mask. NDWI, MDWI, AWEInsh, AWEIsh, and WRI indices were computed to identify ponds and other wetlands. Computation of various water indices, including NDWI (Normalized Difference Water Index), MNDWI (Modified Normalized Difference Water Index), AWEInsh (Automated Water Extraction Index), AWEIsh (Automated Water Extraction Index with shadows), and WRI (Water Ratio Index) was applied to Sentinel-2 imagery for effective mapping and monitoring of water bodies using the following equations:
NDWI = (NIR − Green)/(NIR + Green)
MNDWI = (Green − SWIR)/(Green + SWIR)
AWEInsh = 4 × (Green − SWIR) − (0.25 × NIR + 2.75 × SWIR)
AWEIsh = 4 × (Green − SWIR) − (0.25 × NIR + 2.75 × SWIR) − (2.5 × Blue)
WRI = Green/Red
where:
  • “NIR” is the reflectance in the near-infrared band.
  • “Red“ is the reflectance in the red band.
  • “Green“ is the reflectance in the green band.
  • “Blue“ is the reflectance in the blue band.
  • “SWIR“ is the reflectance in the shortwave infrared band.
This is to overcome the limitation due to single-date cloud cover imagery. We set a conservative threshold beyond which we would exclude aquaculture development. This led to the exclusion of various classes, such as built-up areas and other LULC, and in rare instances, this may have also included shrimp ponds. If any gaps arise in any class, this class can be reclassified, and an initial classification map will be prepared, which will be used in secondary supervised classification.

3.2. Separation of Streams Using LULC Vectorization

Wetlands and water bodies classes for the 2019 and 2022 cropping years were separated. Vectorization was applied to the water bodies to identify stream networks. Naturally developed stream networks and created aquaculture ponds can be distinguished from one another by the compact geometries of the streams. A water bodies masked raster was used for supervised classification with training points.

3.3. Supervised Classification of Ponds to Separate Shrimp Ponds

This study employed the Supervised Classification approach by using Maximum Likelihood Classification using ERDAS. The training samples for other ponds and water bodies were selected from Google Earth images and field survey data. The total number of training samples selected was 45 for shrimp ponds and 25 for other ponds. A minimum of 70 pixels was ensured for each sample to guarantee accuracy.

3.4. Accuracy Assessment

A total of 56 stratified, randomly distributed validation samples were used to determine the accuracy of Cai Doi Vam’s final shrimp ponds map and overall accuracies [55]. The columns of an error matrix contain the ground survey data points, and the rows represent the results of the classified crop maps [56]. A frequently used measure is Kappa [57], representing the agreement among users and producers regarding accuracy from reference ground survey data.

4. Results and Discussion

4.1. Spatial Distribution of LULC

Sentinel 2-based water indices, which are helpful in overcoming mixed classification or missed water pixels in single imagery, are used in developing binary water masks to separate pond water from the land around it. But in Sentinel 2-based water indices, shrimp ponds do not have clear boundaries due to their spatial resolution. Indices like MNDWI and AWEI, in particular, utilize the SWIR band, which is even coarser compared to other visible bands in their calculation (Figure 3).
After initial unsupervised classification for the LULC of the study area, it is observed that shrimp ponds are well connected or situated near a stream network. Ponds are very closely situated in built-up areas, and bunds are mostly covered by vegetation. Other ponds are structures with mangroves situated inside the ponds or abandoned ponds. Preliminary LULC maps of both years are shown in Figure 4. There is a clear reduction in water bodies and other LULC compared to vegetation. This is due to the growth of mangroves and flora in ponds, as well as the fact that barren land and dry soil are now covered by vegetation. This decrease in water bodies suggests a decrease in the areas used for aquaculture; however, a comprehensive change detection analysis will be available after distinguishing these water bodies.
But due to the common characteristics of water bodies and similar pixel values, they resulted in mixed classes of shrimp ponds, other ponds, and stream networks. To eliminate these water bodies, classes were separated after unsupervised classification using Vectorization utilizing the unique structure of stream networks.

4.2. Streams Vectorization

The water bodies class (raster) obtained from the initial classification was converted into vectors. With the help of the Vectorization of water bodies, streams were identified using their structure, as shown in Figure 5. These stream network identifications are helpful in separating ponds and also in monitoring shrimp pond waste disposal methods and the quality of wastewater.

4.3. Spatial Distribution of Shrimp Ponds/Fishponds

The shrimp pond maps were prepared using 3 m resolution for the years 2019 and 2022 (Figure 6 and Figure 7). Shrimp Ponds, Other Ponds, Streams, and Other LULC were delineated. Targeted classes like Shrimp ponds, Other Ponds, and Streams were classified with better accuracy than the other classes because of the spectral resolution of the imagery, which is a tradeoff when classifying very high-resolution imagery. Built-up and other LULC were provided as a single class in the Final Maps. Other LULC classes include barren land, along with embankments of ponds for the case of 2019, while in 2022, these are covered by vegetation. The stream network consists only of major water supply channels, and it does not include those microchannels contributing to individual ponds. Changes in shrimp pond structures were clearly seen within the enlarged area itself, i.e., the conversion of larger ponds into a number of smaller ponds (within the enlarged view, we can observe two long ponds converted into eight smaller ponds) as well as the increased total number of shrimp ponds.
The Cai Doi Canal is surrounded by the majority of shrimp ponds. A more detailed view of each class’s change can be seen in the final maps of shrimp ponds (Figure 6 and Figure 7).
Between 2019 and 2022, an area of 26 ha of shrimp ponds (15%), 337 ha of other ponds (33%), and 42 ha of streams diminished or dried out. This change, on the other hand, was concealed by vegetation, as 650 ha of land cover increased in vegetation class, which is nearly equivalent to the area lost under water bodies. It has been observed that the vegetation-covered area increased by about 115% in 2022 compared to 2019, whereas other land uses, like shrimp ponds, other ponds, and other LULC, showed declines (Table 2).

4.4. Accuracy Assessment

The Overall accuracy of the shrimp pond classification for 2019 was nearly 87%, whereas shrimp ponds class have 90% accuracy. An error matrix was generated for Cai Doi Vam providing producers, users, and overall accuracies (Table 1).
Table 3 shows the accuracy assessment of 2022 shrimp pond classification with same 56 sample points used for the accuracy assessment. An overall accuracy of 89% was obtained because the cloud cover was mostly in other LULC, and the vegetation area was mixed with cloud cover. But the targeted shrimp ponds have more than 90% accuracy and the misclassified listed as other ponds.

4.5. Change Detection in Shrimp Ponds

Triple sat and Jilin data helped in identifying shrimp ponds with up to 90% accuracy, but in order to achieve this high accuracy, the cloud cover has to be low. Change detection was carried out for these shrimp ponds for those two different years, and it was identified that 639 ha of shrimp ponds were left dry in 2022 for the entire Phu Tan district, of which 66 ha was in the Cai Doi Vam sub-district itself (Figure 8). Further, 39 ha of other ponds in 2019 were converted into shrimp ponds in 2022.
Aquaculture has tremendous potential to aid in global food security, making the prediction of pond production volumes a crucial research goal for the coming years. Quantitative data on aquaculture production at both the national and subnational levels is accessible but typically with a lack of precision. In this study, we compiled annual statistics for two years on aquaculture productivity, focusing mostly on shrimp ponds. Extreme weather events such as storms or flooding might have damaged ponds, leading to their reduction in size or abandonment. Natural processes like erosion, sedimentation, and coastal dynamics can also impact LULC changes, particularly in coastal regions like Cai Doi Vam [58]. Sea-level rise, storm surges, and river dynamics can alter coastal landscapes and influence the distribution of ponds and vegetation. Government initiatives to promote ecological restoration and environmental awareness prompted some farmers to restore or convert abandoned ponds back into natural vegetation to address ecological concerns [59,60].

4.6. Discussion on Monitoring Shrimp Ponds Using RS Technology

It is challenging to identify individual ponds from the mixed pixels in the 30-m or 10-m spatial resolution satellite images, and this is why this study focuses on the extraction of aquaculture ponds from high spatial resolution imagery for mapping [46,61,62]. It is challenging for conventional classification techniques or a single spectral index to effectively classify the aquaculture ponds because these ponds are also a sort of water body split by embankments into a large network of smaller ponds [63,64]. By combining spectral data, spatial features, and structural features, we were able to build a system that would let the smaller aquaculture ponds be taken out on a regional scale. Water bodies are typically extracted via spectral index construction, and there are a variety of such indices. The most well known are NDWI, MNDWI, WRI, and AWEI (including AWEIsh and AWEInsh) [65]. Shrimp ponds mapped using single-date imagery for two different time periods of 2019 and 2022 provide us with valuable information on the changes in shrimp cultivation. We observed an overall decrease in the area under shrimp ponds over these two years. The use of remote sensing technology to monitor changes in the size and the number of ponds and frequent mapping using EO data enable us to have reliable data to predict production volume in one area ahead of time. This kind of information is valuable for buyers and processors, as they can adjust their exporting volume or arrange other procurement channels to cover the loss when a decrease in production is predicted. This information is also helpful in policy making towards sustainable production for future years [66]. For example, the government or international organizations can monitor whether the coastal areas have been developed for aquaculture use illegally and, if so, to what extent. Water contamination due to the use of chemicals is a major concern for shrimp farming sustainability. While the current system focuses on mapping aquaculture areas, future iterations could incorporate remote sensing techniques sensitive to water quality. Integrating multispectral or hyperspectral imagery could facilitate the detection of chemical pollution events, providing an early warning system to mitigate potential losses and protect the environment.
We also note that change detection studies with this imagery have limitations: DMC3/Triplesat has low cloud coverage; however, it also has a little lower spatial resolution compared to Jilin. Further, Jilin-1’s overall accuracy was 2% higher than DMC3/Triplesat because of comparatively greater spatial resolution. This high resolution enabled us to extract even smaller shrimp ponds very clearly, compared to what we can do with the Sentinel imagery. Higher-resolution imagery offers more detailed information, enabling better discrimination of aquaculture ponds and associated features. On the other hand, lower-resolution imagery may not capture fine-scale features but can still provide an overview of the larger aquaculture landscape. Future research should explore the trade-offs between resolution and mapping accuracy to optimize the system’s performance.
Integrating periodic satellite imagery updates the system and helps identify changes in aquaculture areas after a natural calamity, such as a flood event. Integrating data from other sources, such as weather data and historical records of flood events, can enhance the system’s ability to understand the relationship between natural calamities and aquaculture losses. This timely information empowers local authorities and farmers to assess the extent of damage and take appropriate measures for recovery and adaptation [67].

5. Conclusions

In conclusion, the successful development of a regional-level coastal pond aquaculture map for two different time periods of 2019 and 2022 of Cai Doi Vam Township, Phu Tan District, Ca Mau Province, using high spatial resolution single-date satellite imagery and ground truth data, marks a significant step forward in sustainable aquaculture management. The system’s integration of advanced satellite imagery technology and ground truth data has allowed for a comprehensive and precise mapping of aquaculture areas, providing valuable insights into the current state of coastal pond aquaculture in the region. The accuracy assessment conducted on the mapping system demonstrates its reliability in producing highly accurate results, thus enabling policymakers and stakeholders to make informed decisions based on trustworthy data. As Jilin and DMC3 satellite data are optical data vulnerable to cloud cover, this hampers the availability of data during cloudy days, especially during rainy seasons. This also results in more mixed classes. Time-series imagery can help in enhancing classification accuracy (in classifying vegetation and water bodies). The categorization may benefit from necessary field-based observations (particularly on the remarks to distinguish between shrimp ponds and other ponds). There is a high possibility of mixed classes while differentiating water bodies because the area is dominated by water. Some water bodies have vegetation and water waves, causing a change in reflectance values leading to misclassification. Triple sat and Jilin were not helpful in built-up and settlement classification due to the absence of the SWIR band.

Author Contributions

P.K.B.: Data curation: Formal analysis, Methodology, Writing—original draft and editing; M.K.G.: Project administration, Resources, Funding acquisition, Supervision, Writing—review and editing; P.P.: Methodology, Visualization; A.S.: Resources, Software; I.M.: Project administration, Resources, Funding acquisition, Writing—review and editing. All authors have read and agreed to the published version of the manuscript.

Funding

This research was funded by the Asian Development Bank Institute and the Japanese Society of Promotion of Sciences KAKENHI, grant numbers JP19H01476 and JP19KK0331.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data will be made available upon request.

Acknowledgments

The authors thankfully acknowledge the financial support from the Asian Development Bank Institute and the Japanese Society of Promotion of Sciences KAKENHI.

Conflicts of Interest

The authors wish to declare that there are no known conflicts of interest associated with this publication.

References

  1. Suzuki, A. Rising Importance of Aquaculture in Asia: Current Status, Issues, and Recommendations; Asian Development Outlook Update Background Paper; Asian Development Bank: Manila, Philippines, 2021. [Google Scholar]
  2. Dhar, U. Asian Development Bank (ADB), Asian Development Outlook 2020: What Drives Innovation in Asia? SAGE Publications Sage India: New Delhi, India, 2021. [Google Scholar]
  3. Anderson, J.; Valderrama, D.; Jory, D. GOAL 2019: Global Shrimp Production Review; GOAL: Portsmouth, NH, USA, 2019. [Google Scholar]
  4. Lam, Y.; Winch, P.J.; Alam Nizame, F.; Broaddus-Shea, E.T.; Harun, G.D.; Surkan, P.J. Salinity and food security in southwest coastal Bangladesh: Impacts on household food production and strategies for adaptation. Food Secur. 2022, 14, 229–248. [Google Scholar]
  5. Parven, A.; Pal, I.; Witayangkurn, A.; Pramanik, M.; Nagai, M.; Miyazaki, H.; Wuthisakkaroon, C. Impacts of disaster and land-use change on food security and adaptation: Evidence from the delta community in Bangladesh. Int. J. Disaster Risk Reduct. 2022, 78, 103119. [Google Scholar]
  6. Abisha, R.; Krishnani, K.K.; Sukhdhane, K.; Verma, A.K.; Brahmane, M.; Chadha, N.K. Sustainable development of climate-resilient aquaculture and culture-based fisheries through adaptation of abiotic stresses: A review. J. Water Clim. Chang. 2022, 13, 2671–2689. [Google Scholar]
  7. Shava, E.; Gunhidzirai, C. Fish farming as an innovative strategy for promoting food security in drought risk regions of Zimbabwe. Jàmbá J. Disaster Risk Stud. 2017, 9, 10. [Google Scholar]
  8. Didar-Ul Islam, S.; Bhuiyan, M.A.H. Impact scenarios of shrimp farming in coastal region of Bangladesh: An approach of an ecological model for sustainable management. Aquac. Int. 2016, 24, 1163–1190. [Google Scholar]
  9. Loc, H.H.; Lixian, M.L.; Park, E.; Dung, T.D.; Shrestha, S.; Yoon, Y.-J. How the saline water intrusion has reshaped the agricultural landscape of the Vietnamese Mekong Delta, a review. Sci. Total Environ. 2021, 794, 148651. [Google Scholar]
  10. Suzuki, A.; Hoang Nam, V. Better management practices and their outcomes in shrimp farming: Evidence from small-scale shrimp farmers in Southern Vietnam. Aquac. Int. 2018, 26, 469–486. [Google Scholar]
  11. Tenório, G.S.; Souza-Filho, P.W.M.; Ramos, E.M.; Alves, P.J.O. Mangrove shrimp farm mapping and productivity on the Brazilian Amazon coast: Environmental and economic reasons for coastal conservation. Ocean Coast. Manag. 2015, 104, 65–77. [Google Scholar]
  12. Wilder, M.; Phuong, N.T. The status of aquaculture in the Mekong Delta region of Vietnam: Sustainable production and combined farming systems. Fish. Sci. 2002, 68 (Suppl. S1), 847–850. [Google Scholar] [CrossRef]
  13. Sebesvari, Z.; Le, H.T.T.; Van Toan, P.; Arnold, U.; Renaud, F.G. Agriculture and water quality in the Vietnamese Mekong Delta. In The Mekong Delta System; Springer: Dordrecht, The Netherlands, 2012; pp. 331–361. [Google Scholar]
  14. Braun, G.; Braun, M.; Kruse, J.; Amelung, W.; Renaud, F.; Khoi, C.; Duong, M.; Sebesvari, Z. Pesticides and antibiotics in permanent rice, alternating rice-shrimp and permanent shrimp systems of the coastal Mekong Delta, Vietnam. Environ. Int. 2019, 127, 442–451. [Google Scholar] [PubMed]
  15. Tan, L.V.; Tran, T.; Loc, H.H. Soil and water quality indicators of diversified farming systems in a saline region of the Mekong Delta, Vietnam. Agriculture 2020, 10, 38. [Google Scholar] [CrossRef]
  16. Lee, G.; Suzuki, A.; Vu, H.N. The determinants of detecting veterinary drug residues: Evidence from shrimp farmers in southern Viet Nam. Aquac. Econ. Manag. 2019, 23, 135–157. [Google Scholar]
  17. Suzuki, A.; Nam, V.H. Blue Revolution in Asia: The Rise of the Shrimp Sector in Vietnam and the Challenges of Disease Control. In Agricultural Development in Asia and Africa: Essays in Honor of Keijiro Otsuka; Springer Nature: Singapore, 2022; pp. 289–303. [Google Scholar]
  18. Leigh, C.; Stewart-Koster, B.; Van Sang, N.; Van Truc, L.; Hiep, L.H.; Xoan, V.B.; Tinh, N.T.N.; An, L.T.; Sammut, J.; Burford, M.A. Rice-shrimp ecosystems in the Mekong Delta: Linking water quality, shrimp and their natural food sources. Sci. Total Environ. 2020, 739, 139931. [Google Scholar] [PubMed]
  19. Gentry, R.R.; Froehlich, H.E.; Grimm, D.; Kareiva, P.; Parke, M.; Rust, M.; Gaines, S.D.; Halpern, B.S. Mapping the global potential for marine aquaculture. Nat. Ecol. Evol. 2017, 1, 1317–1324. [Google Scholar]
  20. Béland, M.; Goïta, K.; Bonn, F.; Pham, T.T.H. Assessment of land-cover changes related to shrimp aquaculture using remote sensing data: A case study in the Giao Thuy District, Vietnam. Int. J. Remote Sens. 2006, 27, 1491–1510. [Google Scholar]
  21. Gusmawati, N.F.; Zhi, C.; Soulard, B.; Lemonnier, H.; Selmaoui-Folcher, N. Aquaculture Pond Precise Mapping in Perancak Estuary, Bali, Indonesia. J. Coast. Res. 2016, 75, 637–641. [Google Scholar]
  22. Seto, K.C.; Fragkias, M. Mangrove conversion and aquaculture development in Vietnam: A remote sensing-based approach for evaluating the Ramsar Convention on Wetlands. Glob. Environ. Chang. 2007, 17, 486–500. [Google Scholar]
  23. Cui, B.; Fei, D.; Shao, G.; Lu, Y.; Chu, J. Extracting raft aquaculture areas from remote sensing images via an improved U-net with a PSE structure. Remote Sens. 2019, 11, 2053. [Google Scholar]
  24. Ottinger, M.; Clauss, K.; Kuenzer, C. Large-scale assessment of coastal aquaculture ponds with Sentinel-1 time series data. Remote Sens. 2017, 9, 440. [Google Scholar]
  25. MacAulay, S.; Ellison, A.R.; Kille, P.; Cable, J. Moving towards improved surveillance and earlier diagnosis of aquatic pathogens: From traditional methods to emerging technologies. Rev. Aquac. 2022, 14, 1813–1829. [Google Scholar] [CrossRef]
  26. Hou, T.; Sun, W.; Chen, C.; Yang, G.; Meng, X.; Peng, J. Marine floating raft aquaculture extraction of hyperspectral remote sensing images based decision tree algorithm. Int. J. Appl. Earth Obs. Geoinf. 2022, 111, 102846. [Google Scholar]
  27. Gumma, M.K.; Amede, T.; Getnet, M.; Pinjarla, B.; Panjala, P.; Legesse, G.; Tilahun, G.; Akker, E.V.D.; Berdel, W.; Keller, C.; et al. Assessing potential locations for flood-based farming using satellite imagery: A case study of Afar region, Ethiopia. Renew. Agric. Food Syst. 2019, 37, S28–S42. [Google Scholar] [CrossRef]
  28. Thenkabail, P.S.; Gumma, M.; Fujii, H.; Namara, R. Spatial models for selecting the most suitable areas of rice cultivation in the Inland Valley Wetlands of Ghana using remote sensing and geographic information systems. J. Appl. Remote Sens. 2009, 3, 033537. [Google Scholar] [CrossRef]
  29. Feyisa, G.L.; Meilby, H.; Fensholt, R.; Proud, S.R. Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery. Remote Sens. Environ. 2014, 140, 23–35. [Google Scholar]
  30. Li, J.; Meng, Y.; Li, Y.; Cui, Q.; Yang, X.; Tao, C.; Wang, Z.; Li, L.; Zhang, W. Accurate water extraction using remote sensing imagery based on normalized difference water index and unsupervised deep learning. J. Hydrol. 2022, 612, 128202. [Google Scholar]
  31. Gumma, M.K.; Panjala, P.; Deevi, K.C.; Bellam, P.K.; Dheeravath, V.; Mohammed, I. Impacts of irrigation tank restoration on water bodies and croplands in Telangana State of India using Landsat time series data and machine learning algorithms. Geocarto Int. 2023, 38, 2186493. [Google Scholar]
  32. Diniz, C.; Cortinhas, L.; Pinheiro, M.L.; Sadeck, L.; Filho, A.F.; Baumann, L.R.F.; Adami, M.; Souza-Filho, P.W.M. A Large-Scale Deep-Learning Approach for Multi-Temporal Aqua and Salt-Culture Mapping. Remote Sens. 2021, 13, 1415. [Google Scholar]
  33. Kurekin, A.A.; Miller, P.I.; Avillanosa, A.L.; Sumeldan, J.D.C. Monitoring of Coastal Aquaculture Sites in the Philippines through Automated Time Series Analysis of Sentinel-1 SAR Images. Remote Sens. 2022, 14, 2862. [Google Scholar] [CrossRef]
  34. Virdis, S.G.P. An object-based image analysis approach for aquaculture ponds precise mapping and monitoring: A case study of Tam Giang-Cau Hai Lagoon, Vietnam. Environ. Monit. Assess. 2014, 186, 117–133. [Google Scholar] [CrossRef] [PubMed]
  35. Sun, Z.; Luo, J.; Yang, J.; Yu, Q.; Zhang, L.; Xue, K.; Lu, L. Nation-Scale Mapping of Coastal Aquaculture Ponds with Sentinel-1 SAR Data Using Google Earth Engine. Remote Sens. 2020, 12, 3086. [Google Scholar]
  36. Gumma, M.K.; Takashi, Y.; Panjala, P.; Deevi, K.C.; Inthavong, V.; Bellam, P.K.; Mohammed, I. Assessment of Cropland Changes Due to New Canals in Vientiane Prefecture of Laos using Earth Observation Data. Smart Agric. Technol. 2023, 4, 100149. [Google Scholar]
  37. Ottinger, M.; Bachofer, F.; Huth, J.; Kuenzer, C. Mapping Aquaculture Ponds for the Coastal Zone of Asia with Sentinel-1 and Sentinel-2 Time Series. Remote Sens. 2021, 14, 153. [Google Scholar] [CrossRef]
  38. Wang, X.; Xiao, X.; Zou, Z.; Hou, L.; Qin, Y.; Dong, J.; Doughty, R.B.; Chen, B.; Zhang, X.; Chen, Y.; et al. Mapping coastal wetlands of China using time series Landsat images in 2018 and Google Earth Engine. ISPRS J. Photogramm. Remote Sens. 2020, 163, 312–326. [Google Scholar]
  39. Chen, B.; Xiao, X.; Li, X.; Pan, L.; Doughty, R.; Ma, J.; Dong, J.; Qin, Y.; Zhao, B.; Wu, Z.; et al. A mangrove forest map of China in 2015: Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform. ISPRS J. Photogramm. Remote Sens. 2017, 131, 104–120. [Google Scholar]
  40. Farda, N. Multi-temporal land use mapping of coastal wetlands area using machine learning in Google earth engine. IOP Conf. Ser. Earth Environ. Sci. 2017, 98, 012042. [Google Scholar] [CrossRef]
  41. Hardy, A.; Oakes, G.; Ettritch, G. Tropical wetland (TropWet) mapping tool: The automatic detection of open and vegetated waterbodies in Google Earth engine for tropical wetlands. Remote Sens. 2020, 12, 1182. [Google Scholar] [CrossRef]
  42. Kolli, M.K.; Opp, C.; Karthe, D.; Pradhan, B. Automatic extraction of large-scale aquaculture encroachment areas using Canny Edge Otsu algorithm in Google Earth Engine–the case study of Kolleru Lake, South India. Geocarto Int. 2022, 37, 11173–11189. [Google Scholar] [CrossRef]
  43. Giri, S.; Samanta, S.; Mondal, P.P.; Basu, O.; Khorat, S.; Chanda, A.; Hazra, S. A geospatial assessment of growth pattern of aquaculture in the Indian Sundarbans Biosphere Reserve. Environ. Dev. Sustain. 2022, 24, 4203–4225. [Google Scholar]
  44. Peralta, R.V.; Tamondong, A.M. Evaluation of Canny Edge Detection and Muti-Threshold Segmentation Technique for Precise Mapping and Inventory of Aquaculture Ponds in Coastal Areas. 2015. Available online: https://api.semanticscholar.org/CorpusID:26455864 (accessed on 21 June 2023).
  45. Lacaux, J.; Tourre, Y.; Vignolles, C.; Ndione, J.; Lafaye, M. Classification of ponds from high-spatial resolution remote sensing: Application to Rift Valley Fever epidemics in Senegal. Remote Sens. Environ. 2007, 106, 66–74. [Google Scholar]
  46. Prasad, K.A.; Ottinger, M.; Wei, C.; Leinenkugel, P. Assessment of coastal aquaculture for India from Sentinel-1 SAR time series. Remote Sens. 2019, 11, 357. [Google Scholar] [CrossRef]
  47. Islam, M.A.; Thenkabail, P.S.; Kulawardhana, R.W.; Alankara, R.; Gunasinghe, S.; Edussriya, C.; Gunawardana, A. Semi-automated methods for mapping wetlands using Landsat ETM+ and SRTM data. Int. J. Remote Sens. 2008, 29, 7077–7106. [Google Scholar] [CrossRef]
  48. Chen, Y.; Song, J.; Yan, C.; Hong, X. Effects of submergence stress at the vegetative growth stage on hybrid rice growth and grain yield in China. Chil. J. Agric. Res. 2021, 81, 191–201. [Google Scholar] [CrossRef]
  49. Minh, H.V.T.; Lavane, K.; Van Ty, T.; Downes, N.K.; Hong, T.T.K.; Kumar, P. Evaluation of the Impact of Drought and Saline Water Intrusion on Rice Yields in the Mekong Delta, Vietnam. Water 2022, 14, 3499. [Google Scholar] [CrossRef]
  50. Pham, H.T.; Bui, L.T. Mechanism of erosion zone formation based on hydrodynamic factor analysis in the Mekong Delta coast, Vietnam. Environ. Technol. Innov. 2023, 30, 103094. [Google Scholar] [CrossRef]
  51. Park, E.; Loc, H.H.; Van Binh, D.; Kantoush, S. The worst 2020 saline water intrusion disaster of the past century in the Mekong Delta: Impacts, causes, and management implications. Ambio 2022, 51, 691–699. [Google Scholar] [CrossRef] [PubMed]
  52. ADB. Climate Risks in the Mekong Delta: Ca Mau and Kien Giang Provinces of Viet Nam; Asian Development Bank: Mandaluyong, Philippines, 2013. [Google Scholar]
  53. Thenkabail, P.; GangadharaRao, P.; Biggs, T.; Krishna, M.; Turral, H. Spectral matching techniques to determine historical land-use/land-cover (LULC) and irrigated areas using time-series 0.1-degree AVHRR pathfinder datasets. Photogramm. Eng. Remote Sens. 2007, 73, 1029–1040. [Google Scholar]
  54. Teluguntla, P.; Thenkabail, P.S.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Oliphant, A.; Poehnelt, J.; Yadav, K.; Rao, M.; Massey, R. Spectral matching techniques (SMTs) and automated cropland classification algorithms (ACCAs) for mapping croplands of Australia using MODIS 250-m time-series (2000–2015) data. Int. J. Digit. Earth 2017, 10, 944–977. [Google Scholar] [CrossRef]
  55. Congalton, R.G.; Green, K. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices; CRC Press: Boca Raton, FL, USA, 2019. [Google Scholar]
  56. Congalton, R.G. A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens. Environ. 1991, 37, 35–46. [Google Scholar] [CrossRef]
  57. Cohen, J. A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 1960, 20, 36–47. [Google Scholar] [CrossRef]
  58. Veettil, B.K.; Ward, R.D.; Quang, N.X.; Trang, N.T.T.; Giang, T.H. Mangroves of Vietnam: Historical development, current state of research and future threats. Estuar. Coast. Shelf Sci. 2019, 218, 212–236. [Google Scholar] [CrossRef]
  59. Phan, V.H.; Dinh, V.T.; Su, Z. Trends in Long-Term Drought Changes in the Mekong River Delta of Vietnam. Remote Sens. 2020, 12, 2974. [Google Scholar] [CrossRef]
  60. Phan, M.H.; Stive, M.J. Managing mangroves and coastal land cover in the Mekong Delta. Ocean Coast. Manag. 2022, 219, 106013. [Google Scholar] [CrossRef]
  61. Ottinger, M.; Clauss, K.; Kuenzer, C. Opportunities and challenges for the estimation of aquaculture production based on earth observation data. Remote Sens. 2018, 10, 1076. [Google Scholar] [CrossRef]
  62. Duan, Y.; Tian, B.; Li, X.; Liu, D.; Sengupta, D.; Wang, Y.; Peng, Y. Tracking changes in aquaculture ponds on the China coast using 30 years of Landsat images. Int. J. Appl. Earth Obs. Geoinf. 2021, 102, 102383. [Google Scholar] [CrossRef]
  63. Alexandridis, T.K.; Topaloglou, C.A.; Lazaridou, E.; Zalidis, G.C. The performance of satellite images in mapping aquacultures. Ocean Coast. Manag. 2008, 51, 638–644. [Google Scholar] [CrossRef]
  64. Xia, Z.; Guo, X.; Chen, R. Automatic extraction of aquaculture ponds based on Google Earth Engine. Ocean Coast. Manag. 2020, 198, 105348. [Google Scholar] [CrossRef]
  65. Veettil, B.K.; Quang, N.X.; Trang, N.T.T. Changes in mangrove vegetation, aquaculture and paddy cultivation in the Mekong Delta: A study from Ben Tre Province, southern Vietnam. Estuar. Coast. Shelf Sci. 2019, 226, 106273. [Google Scholar] [CrossRef]
  66. Lappe, R.; Ullmann, T.; Bachofer, F. State of the Vietnamese coast—Assessing three decades (1986 to 2021) of coastline dynamics using the Landsat archive. Remote Sens. 2022, 14, 2476. [Google Scholar] [CrossRef]
  67. Xu, Y.; Hu, Z.; Zhang, Y.; Wang, J.; Yin, Y.; Wu, G. Mapping aquaculture areas with Multi-Source spectral and texture features: A case study in the pearl river basin (Guangdong), China. Remote Sens. 2021, 13, 4320. [Google Scholar] [CrossRef]
Agriengineering 05 00089 g001
Figure 1. (a) Location of the Study Area Cai Doi Vam Subdistrict of Phu Tan District, Ca Mau Province of Viet Nam in Asia. (b) The Detailed View of the Study Area and Neighboring Area represented with satellite data of DMC3 (Triplesat) in March of 2019 in FCC of NIR, Red, and Green.
Figure 1. (a) Location of the Study Area Cai Doi Vam Subdistrict of Phu Tan District, Ca Mau Province of Viet Nam in Asia. (b) The Detailed View of the Study Area and Neighboring Area represented with satellite data of DMC3 (Triplesat) in March of 2019 in FCC of NIR, Red, and Green.
Agriengineering 05 00089 g001
Agriengineering 05 00089 g002
Figure 2. The methodology used to map shrimp ponds using high spatial resolution data.
Figure 2. The methodology used to map shrimp ponds using high spatial resolution data.
Agriengineering 05 00089 g002
Agriengineering 05 00089 g003
Figure 3. Sentinal-2 water indices NDWI, MNDWI, WRI, AWEInsh, AWEIsh base water bodies masks.
Figure 3. Sentinal-2 water indices NDWI, MNDWI, WRI, AWEInsh, AWEIsh base water bodies masks.
Agriengineering 05 00089 g003
Agriengineering 05 00089 g004
Figure 4. LULC Map of Cai Doi Vam for 2019 and 2022 with enlarged view.
Figure 4. LULC Map of Cai Doi Vam for 2019 and 2022 with enlarged view.
Agriengineering 05 00089 g004
Agriengineering 05 00089 g005
Figure 5. Stream network Map with an enlarged view over satellite imagery.
Figure 5. Stream network Map with an enlarged view over satellite imagery.
Agriengineering 05 00089 g005
Agriengineering 05 00089 g006
Figure 6. (a) Shrimp pond map of 2019 based on DMC3, (b) Enlarged view of classified ponds, (c) Enlarged view of satellite imagery.
Figure 6. (a) Shrimp pond map of 2019 based on DMC3, (b) Enlarged view of classified ponds, (c) Enlarged view of satellite imagery.
Agriengineering 05 00089 g006
Agriengineering 05 00089 g007
Figure 7. (a) Shrimp pond map of 2022 based on Jilin, (b) Enlarged view of classified ponds, (c) Enlarged view of satellite imagery.
Figure 7. (a) Shrimp pond map of 2022 based on Jilin, (b) Enlarged view of classified ponds, (c) Enlarged view of satellite imagery.
Agriengineering 05 00089 g007
Agriengineering 05 00089 g008
Figure 8. Change of shrimp ponds from 2019 to 2022.
Figure 8. Change of shrimp ponds from 2019 to 2022.
Agriengineering 05 00089 g008
Table 1. Satellite data with their characteristics and specific utilization.
Table 1. Satellite data with their characteristics and specific utilization.
SatelliteBands—Spatial ResolutionBandsUtilization
DMC3/TripleSatPan:0.8 m,
Multispectral: 3.2 m		Pan, Blue, Green, Red, NIR2019 Shrimp ponds Map
Jilin-1KF01APan: 0.75 m,
Multispectral: 3 m		Pan, Blue, Green, Red, NIR2022 Shrimp Ponds Map
Sentinel-2B2, B3, B8: 10 m,
B11, B12: 20 m		B1-B8, B8a, B9-B12Water bodies Mask (through different water Indices)
Table 2. LULC Change statistics from 2019 to 2022.
Table 2. LULC Change statistics from 2019 to 2022.
LULC2022 (ha)2019 (ha)Change (ha)% Change
Shrimp Ponds148.11174.71−26.60−15.20
Other Ponds682.511020.01−337.50−33.08
Streams67.48109.56−42.08−38.40
Vegetation1210.77560.67650.10115.95
Other LULC55.09299.08−243.99−81.58
Table 3. Overall accuracy with producer’s, user’s accuracy and Kappa coefficient of 2019 & 2022.
Table 3. Overall accuracy with producer’s, user’s accuracy and Kappa coefficient of 2019 & 2022.
LULC ClassReference TotalsClassified TotalsNumber CorrectProducer’s AccuracyUser’s
Accuracy		Kappa
Coefficient
a. 2019
01. Shrimp Ponds11111090.91%90.91%0.8255
02. Ponds (Other)222622100.00%84.62%
03. Streams76685.71%100.00%
04. Vegetation14111178.57%100.00%
05. Other LULC200
Totals565649
Overall Classification Accuracy87.50%
b. 2022
01. Shrimp Pond109990.00%100.00%0.8531
02. Ponds (Other)21201885.71%90.00%
03. Streams65583.33%100.00%
04. Vegetation161916100.00%84.21%
05. Other LULC21150.00%100.00%
Totals565650
Overall Classification Accuracy89.29%
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Bellam, P.K.; Gumma, M.K.; Panjala, P.; Mohammed, I.; Suzuki, A. Mapping Shrimp Pond Dynamics: A Spatiotemporal Study Using Remote Sensing Data and Machine Learning. AgriEngineering 2023, 5, 1432-1447. https://doi.org/10.3390/agriengineering5030089

AMA Style

Bellam PK, Gumma MK, Panjala P, Mohammed I, Suzuki A. Mapping Shrimp Pond Dynamics: A Spatiotemporal Study Using Remote Sensing Data and Machine Learning. AgriEngineering. 2023; 5(3):1432-1447. https://doi.org/10.3390/agriengineering5030089

Chicago/Turabian Style

Bellam, Pavan Kumar, Murali Krishna Gumma, Pranay Panjala, Ismail Mohammed, and Aya Suzuki. 2023. "Mapping Shrimp Pond Dynamics: A Spatiotemporal Study Using Remote Sensing Data and Machine Learning" AgriEngineering 5, no. 3: 1432-1447. https://doi.org/10.3390/agriengineering5030089

Article Metrics

Back to TopTop