Sensors

Research

12 pages, 12604 KiB

Open AccessArticle

A New Method for Ground-Based Optical Polarization Observation of the Moon

by Weinan Wang, Jinsong Ping, Wenzhao Zhang, Mingyuan Wang, Hanlin Ye, Xingwei Han and Songfeng Kou

Sensors 2024, 24(8), 2580; https://doi.org/10.3390/s24082580 - 18 Apr 2024

Viewed by 287

Abstract

As a natural satellite of the Earth, the moon is a prime target for planetary remote sensing exploration. However, lunar polarization studies are not popular in the planetary science community. Polarimetry of the lunar surface had not been carried out from a spacecraft [...] Read more.

As a natural satellite of the Earth, the moon is a prime target for planetary remote sensing exploration. However, lunar polarization studies are not popular in the planetary science community. Polarimetry of the lunar surface had not been carried out from a spacecraft until the Korean lunar exploration program was initiated. In previous polarization observations of the moon, images of different polarization states were obtained by a rotating linear polarizer. This method is not well suited for future polarization observations from space-based spacecraft. To this end, we present a new kind of polarized observation of the moon using a division of a focal-plane polarization camera and propose a pipeline on the processing method of the polarization observation of the moon. We obtain a map of the degree of white-light polarization on the nearside of the moon through polarization observation, data processing, and correction. The observation and data processing methods presented in this study have the potential to serve as a reference for analyzing polarization observation data from future orbiting spacecraft. These are expected to lead to new discoveries in the fields of astronomy and planetary science. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

32 pages, 34067 KiB

Open AccessArticle

Automated Mapping of Land Cover Type within International Heterogenous Landscapes Using Sentinel-2 Imagery with Ancillary Geospatial Data

by Kristofer Lasko, Francis D. O’Neill and Elena Sava

Sensors 2024, 24(5), 1587; https://doi.org/10.3390/s24051587 - 29 Feb 2024

Viewed by 1158

Abstract

A near-global framework for automated training data generation and land cover classification using shallow machine learning with low-density time series imagery does not exist. This study presents a methodology to map nine-class, six-class, and five-class land cover using two dates (winter and non-winter) [...] Read more.

A near-global framework for automated training data generation and land cover classification using shallow machine learning with low-density time series imagery does not exist. This study presents a methodology to map nine-class, six-class, and five-class land cover using two dates (winter and non-winter) of a Sentinel-2 granule across seven international sites. The approach uses a series of spectral, textural, and distance decision functions combined with modified ancillary layers (such as global impervious surface and global tree cover) to create binary masks from which to generate a balanced set of training data applied to a random forest classifier. For the land cover masks, stepwise threshold adjustments were applied to reflectance, spectral index values, and Euclidean distance layers, with 62 combinations evaluated. Global (all seven scenes) and regional (arid, tropics, and temperate) adaptive thresholds were computed. An annual 95th and 5th percentile NDVI composite was used to provide temporal corrections to the decision functions, and these corrections were compared against the original model. The accuracy assessment found that the regional adaptive thresholds for both the two-date land cover and the temporally corrected land cover could accurately map land cover type within nine-class (68.4% vs. 73.1%), six-class (79.8% vs. 82.8%), and five-class (80.1% vs. 85.1%) schemes. Lastly, the five-class and six-class models were compared with a manually labeled deep learning model (Esri), where they performed with similar accuracies (five classes: Esri 80.0 ± 3.4%, region corrected 85.1 ± 2.9%). The results highlight not only performance in line with an intensive deep learning approach, but also that reasonably accurate models can be created without a full annual time series of imagery. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

18 pages, 8081 KiB

Open AccessArticle

Leveraging Remote Sensing Data for Yield Prediction with Deep Transfer Learning

by Florian Huber, Alvin Inderka and Volker Steinhage

Sensors 2024, 24(3), 770; https://doi.org/10.3390/s24030770 - 24 Jan 2024

Cited by 1 | Viewed by 844

Abstract

Remote sensing data represent one of the most important sources for automized yield prediction. High temporal and spatial resolution, historical record availability, reliability, and low cost are key factors in predicting yields around the world. Yield prediction as a machine learning task is [...] Read more.

Remote sensing data represent one of the most important sources for automized yield prediction. High temporal and spatial resolution, historical record availability, reliability, and low cost are key factors in predicting yields around the world. Yield prediction as a machine learning task is challenging, as reliable ground truth data are difficult to obtain, especially since new data points can only be acquired once a year during harvest. Factors that influence annual yields are plentiful, and data acquisition can be expensive, as crop-related data often need to be captured by experts or specialized sensors. A solution to both problems can be provided by deep transfer learning based on remote sensing data. Satellite images are free of charge, and transfer learning allows recognition of yield-related patterns within countries where data are plentiful and transfers the knowledge to other domains, thus limiting the number of ground truth observations needed. Within this study, we examine the use of transfer learning for yield prediction, where the data preprocessing towards histograms is unique. We present a deep transfer learning framework for yield prediction and demonstrate its successful application to transfer knowledge gained from US soybean yield prediction to soybean yield prediction within Argentina. We perform a temporal alignment of the two domains and improve transfer learning by applying several transfer learning techniques, such as

L^{2}

-SP, BSS, and layer freezing, to overcome catastrophic forgetting and negative transfer problems. Lastly, we exploit spatio-temporal patterns within the data by applying a Gaussian process. We are able to improve the performance of soybean yield prediction in Argentina by a total of 19% in terms of RMSE and 39% in terms of

R^{2}

compared to predictions without transfer learning and Gaussian processes. This proof of concept for advanced transfer learning techniques for yield prediction and remote sensing data in the form of histograms can enable successful yield prediction, especially in emerging and developing countries, where reliable data are usually limited. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

16 pages, 12318 KiB

Open AccessArticle

Red Tide Detection Method Based on Improved U-Net Model-Taking GOCI Data in East China Sea as an Example

by Yanling Han, Tianhong Ding, Pengxia Cui, Xiaotong Wang, Bowen Zheng, Xiaojing Shen, Zhenling Ma, Yun Zhang, Haiyan Pan and Shuhu Yang

Sensors 2023, 23(22), 9195; https://doi.org/10.3390/s23229195 - 15 Nov 2023

Viewed by 668

Abstract

In the coastal areas of China, the eutrophication of seawater leads to the continuous occurrence of red tide, which has caused great damage to Marine fisheries and aquatic resources. Therefore, the detection and prediction of red tide have important research significance. The rapid [...] Read more.

In the coastal areas of China, the eutrophication of seawater leads to the continuous occurrence of red tide, which has caused great damage to Marine fisheries and aquatic resources. Therefore, the detection and prediction of red tide have important research significance. The rapid development of optical remote sensing technology and deep-learning technology provides technical means for realizing large-scale and high-precision red tide detection. However, the difficulty of the accurate detection of red tide edges with complex boundaries limits the further improvement of red tide detection accuracy. In view of the above problems, this paper takes GOCI data in the East China Sea as an example and proposes an improved U-Net red tide detection method. In the improved U-Net method, NDVI was introduced to enhance the characteristic information of the red tide to improve the separability between the red tide and seawater. At the same time, the ECA channel attention mechanism was introduced to give different weights according to the influence of different bands on red tide detection, and the spectral characteristics of different channels were fully mined to further extract red tide characteristics. A shallow feature extraction module based on Atrous Spatial Pyramid Convolution (ASPC) was designed to improve the U-Net model. The red tide feature information in a multi-scale context was fused under multiple sampling rates to enhance the model’s ability to extract features at different scales. The problem of limited accuracy improvement in red tide edge detection with complex boundaries is solved via the fusion of deep and shallow features and multi-scale spatial features. Compared with other methods, the method proposed in this paper achieves better results and can detect red tide edges with complex boundaries, and the accuracy, precision, recall, and F1-score are 95.90%, 97.15%, 91.53%, and 0.94, respectively. In addition, the red tide detection experiments in other regions with relatively concentrated distribution also prove that the method has good applicability. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

18 pages, 7549 KiB

Open AccessArticle

Atmospheric Thermodynamic Profiling through the Use of a Micro-Pulse Raman Lidar System: Introducing the Compact Raman Lidar MARCO

by Paolo Di Girolamo, Noemi Franco, Marco Di Paolantonio, Donato Summa and Davide Dionisi

Sensors 2023, 23(19), 8262; https://doi.org/10.3390/s23198262 - 06 Oct 2023

Viewed by 875

Abstract

It was for a long time believed that lidar systems based on the use of high-repetition micro-pulse lasers could be effectively used to only stimulate atmospheric elastic backscatter echoes, and thus were only exploited in elastic backscatter lidar systems. Their application to stimulate [...] Read more.

It was for a long time believed that lidar systems based on the use of high-repetition micro-pulse lasers could be effectively used to only stimulate atmospheric elastic backscatter echoes, and thus were only exploited in elastic backscatter lidar systems. Their application to stimulate rotational and roto-vibrational Raman echoes, and consequently, their exploitation in atmospheric thermodynamic profiling, was considered not feasible based on the technical specifications possessed by these laser sources until a few years ago. However, recent technological advances in the design and development of micro-pulse lasers, presently achieving high UV average powers (1–5 W) and small divergences (0.3–0.5 mrad), in combination with the use of large aperture telescopes (0.3–0.4 m diameter primary mirrors), allow one to presently develop micro-pulse laser-based Raman lidars capable of measuring the vertical profiles of atmospheric thermodynamic parameters, namely water vapor and temperature, both in the daytime and night-time. This paper is aimed at demonstrating the feasibility of these measurements and at illustrating and discussing the high achievable performance level, with a specific focus on water vapor profile measurements. The technical solutions identified in the design of the lidar system and their technological implementation within the experimental setup of the lidar prototype are also carefully illustrated and discussed. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

20 pages, 15854 KiB

Open AccessArticle

Hyperspectral Infrared Observations of Arctic Snow, Sea Ice, and Non-Frozen Ocean from the RV Polarstern during the MOSAiC Expedition October 2019 to September 2020

by Ester Nikolla, Robert Knuteson and Jonathan Gero

Sensors 2023, 23(12), 5755; https://doi.org/10.3390/s23125755 - 20 Jun 2023

Cited by 1 | Viewed by 1104

Abstract

This study highlights hyperspectral infrared observations from the Marine-Atmospheric Emitted Radiance Interferometer (M-AERI) collected as part of the Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Mobile Facility (AMF) deployment on the icebreaker RV Polarstern during the Multidisciplinary drifting Observatory for the Study [...] Read more.

This study highlights hyperspectral infrared observations from the Marine-Atmospheric Emitted Radiance Interferometer (M-AERI) collected as part of the Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Mobile Facility (AMF) deployment on the icebreaker RV Polarstern during the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition from October 2019 to September 2020. The ARM M-AERI directly measures the infrared radiance emission spectrum between 520 cm⁻¹ and 3000 cm⁻¹ (19.2–3.3 μm) at 0.5 cm⁻¹ spectral resolution. These ship-based observations provide a valuable set of radiance data for the modeling of snow/ice infrared emission as well as validation data for the assessment of satellite soundings. Remote sensing using hyperspectral infrared observations provides valuable information on sea surface properties (skin temperature and infrared emissivity), near-surface air temperature, and temperature lapse rate in the lowest kilometer. Comparison of the M-AERI observations with those from the DOE ARM meteorological tower and downlooking infrared thermometer are generally in good agreement with some notable differences. Operational satellite soundings from the NOAA-20 satellite were also assessed using ARM radiosondes launched from the RV Polarstern and measurements of the infrared snow surface emission from the M-AERI showing reasonable agreement. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

Review

Jump to: Research, Other

30 pages, 10951 KiB

Open AccessReview

A Review on Recent Deep Learning-Based Semantic Segmentation for Urban Greenness Measurement

by Doo Hong Lee, Hye Yeon Park and Joonwhoan Lee

Sensors 2024, 24(7), 2245; https://doi.org/10.3390/s24072245 - 31 Mar 2024

Viewed by 492

Abstract

Accurate urban green space (UGS) measurement has become crucial for landscape analysis. This paper reviews the recent technological breakthroughs in deep learning (DL)-based semantic segmentation, emphasizing efficient landscape analysis, and integrating greenness measurements. It explores quantitative greenness measures applied through semantic segmentation, categorized [...] Read more.

Accurate urban green space (UGS) measurement has become crucial for landscape analysis. This paper reviews the recent technological breakthroughs in deep learning (DL)-based semantic segmentation, emphasizing efficient landscape analysis, and integrating greenness measurements. It explores quantitative greenness measures applied through semantic segmentation, categorized into the plan view- and the perspective view-based methods, like the Land Class Classification (LCC) with green objects and the Green View Index (GVI) based on street photographs. This review navigates from traditional to modern DL-based semantic segmentation models, illuminating the evolution of the urban greenness measures and segmentation tasks for advanced landscape analysis. It also presents the typical performance metrics and explores public datasets for constructing these measures. The results show that accurate (semantic) segmentation is inevitable not only for fine-grained greenness measures but also for the qualitative evaluation of landscape analyses for planning amidst the incomplete explainability of the DL model. Also, the unsupervised domain adaptation (UDA) in aerial images is addressed to overcome the scale changes and lack of labeled data for fine-grained greenness measures. This review contributes to helping researchers understand the recent breakthroughs in DL-based segmentation technology for challenging topics in UGS research. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

Other

Jump to: Research, Review

21 pages, 2010 KiB

Open AccessSystematic Review

Forestry Applications of Space-Borne LiDAR Sensors: A Worldwide Bibliometric Analysis

by Fernando J. Aguilar, Francisco A. Rodríguez, Manuel A. Aguilar, Abderrahim Nemmaoui and Flor Álvarez-Taboada

Sensors 2024, 24(4), 1106; https://doi.org/10.3390/s24041106 - 08 Feb 2024

Viewed by 729

Abstract

The 21st century has seen the launch of new space-borne sensors based on LiDAR (light detection and ranging) technology developed in the second half of the 20th century. Nowadays, these sensors offer novel opportunities for mapping terrain and canopy heights and estimating aboveground [...] Read more.

The 21st century has seen the launch of new space-borne sensors based on LiDAR (light detection and ranging) technology developed in the second half of the 20th century. Nowadays, these sensors offer novel opportunities for mapping terrain and canopy heights and estimating aboveground biomass (AGB) across local to regional scales. This study aims to analyze the scientific impact of these sensors on large-scale forest mapping to retrieve 3D canopy information, monitor forest degradation, estimate AGB, and model key ecosystem variables such as primary productivity and biodiversity. A worldwide bibliometric analysis of this topic was carried out based on up to 412 publications indexed in the Scopus database during the period 2004–2022. The results showed that the number of published documents increased exponentially in the last five years, coinciding with the commissioning of two new LiDAR space missions: Ice, Cloud, and Land Elevation Satellite (ICESat-2) and Global Ecosystem Dynamics Investigation (GEDI). These missions have been providing data since 2018 and 2019, respectively. The journal that demonstrated the highest productivity in this field was “Remote Sensing” and among the leading contributors, the top five countries in terms of publications were the USA, China, the UK, France, and Germany. The upward trajectory in the number of publications categorizes this subject as a highly trending research topic, particularly in the context of improving forest resource management and participating in global climate treaty frameworks that require monitoring and reporting on forest carbon stocks. In this context, the integration of space-borne data, including imagery, SAR, and LiDAR, is anticipated to steer the trajectory of this research in the upcoming years. Full article

(This article belongs to the Special Issue Feature Papers in Remote Sensors 2023)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Feature Papers in Remote Sensors 2023

Share This Special Issue

Special Issue Editors

Special Issue Information

Published Papers (8 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI