Research

14 pages, 27273 KiB

Open AccessArticle

Comprehensive Analysis of Model Errors in Blueberry Detection and Maturity Classification: Identifying Limitations and Proposing Future Improvements in Agricultural Monitoring

by Cristhian A. Aguilera, Carola Figueroa-Flores, Cristhian Aguilera and Cesar Navarrete

Agriculture 2024, 14(1), 18; https://doi.org/10.3390/agriculture14010018 - 22 Dec 2023

Viewed by 817

Abstract

In blueberry farming, accurately assessing maturity is critical to efficient harvesting. Deep Learning solutions, which are increasingly popular in this area, often undergo evaluation through metrics like mean average precision (mAP). However, these metrics may only partially capture the actual performance of the [...] Read more.

In blueberry farming, accurately assessing maturity is critical to efficient harvesting. Deep Learning solutions, which are increasingly popular in this area, often undergo evaluation through metrics like mean average precision (mAP). However, these metrics may only partially capture the actual performance of the models, especially in settings with limited resources like those in agricultural drones or robots. To address this, our study evaluates Deep Learning models, such as YOLOv7, RT-DETR, and Mask-RCNN, for detecting and classifying blueberries. We perform these evaluations on both powerful computers and embedded systems. Using Type-Influence Detector Error (TIDE) analysis, we closely examine the accuracy of these models. Our research reveals that partial occlusions commonly cause errors, and optimizing these models for embedded devices can increase their speed without losing precision. This work improves the understanding of object detection models for blueberry detection and maturity estimation. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

23 pages, 1361 KiB

Open AccessArticle

Data-Driven Analysis and Machine Learning-Based Crop and Fertilizer Recommendation System for Revolutionizing Farming Practices

by Christine Musanase, Anthony Vodacek, Damien Hanyurwimfura, Alfred Uwitonze and Innocent Kabandana

Agriculture 2023, 13(11), 2141; https://doi.org/10.3390/agriculture13112141 - 13 Nov 2023

Cited by 2 | Viewed by 3233

Abstract

Agriculture plays a key role in global food security. Agriculture is critical to global food security and economic development. Precision farming using machine learning (ML) and the Internet of Things (IoT) is a promising approach to increasing crop productivity and optimizing resource use. [...] Read more.

Agriculture plays a key role in global food security. Agriculture is critical to global food security and economic development. Precision farming using machine learning (ML) and the Internet of Things (IoT) is a promising approach to increasing crop productivity and optimizing resource use. This paper presents an integrated crop and fertilizer recommendation system aimed at optimizing agricultural practices in Rwanda. The system is built on two predictive models: a machine learning model for crop recommendations and a rule-based fertilization recommendation model. The crop recommendation system is based on a neural network model trained on a dataset of major Rwandan crops and their key growth parameters such as nitrogen, phosphorus, potassium levels, and soil pH. The fertilizer recommendation system uses a rule-based approach to provide personalized fertilizer recommendations based on pre-compiled tables. The proposed prediction model achieves 97% accuracy. The study makes a significant contribution to the field of precision agriculture by providing decision support tools that combine artificial intelligence and domain knowledge. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

19 pages, 10221 KiB

Open AccessArticle

Artificial Intelligence-Based Fault Diagnosis and Prediction for Smart Farm Information and Communication Technology Equipment

by Hyeon O. Choe and Meong-Hun Lee

Agriculture 2023, 13(11), 2124; https://doi.org/10.3390/agriculture13112124 - 10 Nov 2023

Cited by 1 | Viewed by 1055

Abstract

Despite the recent increase in smart farming practices, system uncertainty and difficulties associated with maintaining farming sites hinder their widespread adoption. Agricultural production systems are extremely sensitive to operational downtime caused by malfunctions because it can damage crops. To resolve this problem, the [...] Read more.

Despite the recent increase in smart farming practices, system uncertainty and difficulties associated with maintaining farming sites hinder their widespread adoption. Agricultural production systems are extremely sensitive to operational downtime caused by malfunctions because it can damage crops. To resolve this problem, the types of abnormal data, the present error determination techniques for each data type, and the accuracy of anomaly data determination based on spatial understanding of the sensed values are classified in this paper. We design and implement a system to detect and predict abnormal data using a recurrent neural network algorithm and diagnose malfunctions using an ontological technique. The proposed system comprises the cloud in charge of the IoT equipment installed in the farm testbed, communication and control, system management, and a common framework based on machine learning and deep learning for fault diagnosis. It exhibits excellent prediction performance, with a root mean square error of 0.073 for the long short-term memory model. Considering the increasing number of agricultural production facilities in recent years, the results of this study are expected to prevent damage to farms due to downtime caused by mistakes, faults, and aging. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

22 pages, 4393 KiB

Open AccessArticle

Combining Neural Architecture Search with Knowledge Graphs in Transformer: Advancing Chili Disease Detection

by Boyu Xie, Qi Su, Beilun Tang, Yan Li, Zhengwu Yang, Jiaoyang Wang, Chenxi Wang, Jingxian Lin and Lin Li

Agriculture 2023, 13(10), 2025; https://doi.org/10.3390/agriculture13102025 - 19 Oct 2023

Viewed by 1143

Abstract

With the advancement in modern agricultural technologies, ensuring crop health and enhancing yield have become paramount. This study aims to address potential shortcomings in the existing chili disease detection methods, particularly the absence of optimized model architecture and in-depth domain knowledge integration. By [...] Read more.

With the advancement in modern agricultural technologies, ensuring crop health and enhancing yield have become paramount. This study aims to address potential shortcomings in the existing chili disease detection methods, particularly the absence of optimized model architecture and in-depth domain knowledge integration. By introducing a neural architecture search (NAS) and knowledge graphs, an attempt is made to bridge this gap, targeting enhanced detection accuracy and robustness. A disease detection model based on the Transformer and knowledge graphs is proposed. Upon evaluating various object detection models on edge computing platforms, it was observed that the dynamic head module surpassed the performance of the multi-head attention mechanism during data processing. The experimental results further indicated that when integrating all the data augmentation methods, the model achieved an optimal mean average precision (mAP) of 0.94. Additionally, the dynamic head module exhibited superior accuracy and recall compared to the traditional multi-head attention mechanism. In conclusion, this research offers a novel perspective and methodology for chili disease detection, with aspirations that the findings will contribute to the further advancement of modern agriculture. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

23 pages, 11199 KiB

Open AccessArticle

A Lightweight Pest Detection Model for Drones Based on Transformer and Super-Resolution Sampling Techniques

by Yuzhe Bai, Fengjun Hou, Xinyuan Fan, Weifan Lin, Jinghan Lu, Junyu Zhou, Dongchen Fan and Lin Li

Agriculture 2023, 13(9), 1812; https://doi.org/10.3390/agriculture13091812 - 14 Sep 2023

Viewed by 1308

Abstract

With the widespread application of drone technology, the demand for pest detection and identification from low-resolution and noisy images captured with drones has been steadily increasing. In this study, a lightweight pest identification model based on Transformer and super-resolution sampling techniques is introduced, [...] Read more.

With the widespread application of drone technology, the demand for pest detection and identification from low-resolution and noisy images captured with drones has been steadily increasing. In this study, a lightweight pest identification model based on Transformer and super-resolution sampling techniques is introduced, aiming to enhance identification accuracy under challenging conditions. The Transformer model was found to effectively capture spatial dependencies in images, while the super-resolution sampling technique was employed to restore image details for subsequent identification processes. The experimental results demonstrated that this approach exhibited significant advantages across various pest image datasets, achieving Precision, Recall, mAP, and FPS scores of 0.97, 0.95, 0.95, and 57, respectively. Especially in the presence of low resolution and noise, this method was capable of performing pest identification with high accuracy. Furthermore, an adaptive optimizer was incorporated to enhance model convergence and performance. Overall, this study offers an efficient and accurate method for pest detection and identification in practical applications, holding significant practical value. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

18 pages, 2573 KiB

Open AccessArticle

A Comprehensive Analysis of Machine Learning-Based Assessment and Prediction of Soil Enzyme Activity

by Yogesh Shahare, Mukund Partap Singh, Prabhishek Singh, Manoj Diwakar, Vijendra Singh, Seifedine Kadry and Lukas Sevcik

Agriculture 2023, 13(7), 1323; https://doi.org/10.3390/agriculture13071323 - 28 Jun 2023

Cited by 2 | Viewed by 1536

Abstract

Different soil characteristics in different parts of India affect agriculture growth. Crop growth and crop production are significantly impacted by healthy soil. Soil enzymes mediate almost all biochemical reactions in the soil. Understanding the biological processes of soil carbon and nitrogen cycling requires [...] Read more.

Different soil characteristics in different parts of India affect agriculture growth. Crop growth and crop production are significantly impacted by healthy soil. Soil enzymes mediate almost all biochemical reactions in the soil. Understanding the biological processes of soil carbon and nitrogen cycling requires defining the significance of prospective elements at the play of soil enzymes and evaluating their activities. A combination of Multiple Linear Regression (MLR), Random Forest (RF) models, and Artificial Neural Networks (ANN) was employed in this study to assess soil enzyme activity, including amylase and urease activity, soil physical properties, such as sand, silt, clay, and soil chemical properties, including organic matter (SOM), nitrogen (N), phosphorus (P), soil organic carbon (SOC), pH, and fertility level. Compared to other methods for estimating soil phosphatase, cellulose, and urease activity, the RF model significantly outperforms the MLR model. In addition, due to its ability to manage dynamic and hierarchical relationships between enzyme activities, the RF model outperforms other models in evaluating soil enzyme activity. This study collected 3972 soil samples from 25 villages in the Bhandara district of Maharashtra, India, with chemical, physical, and biological parameters. Overall, 99% accuracy was achieved for cellulase enzyme activity and 94% for N-acetyl-glucosaminidase enzyme activity using the Random Forest model. Crops have been suggested based on the best performance accuracy algorithms and evaluation performance metrics. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

11 pages, 956 KiB

Open AccessArticle

Identification of Characteristic Parameters in Seed Yielding of Selected Varieties of Industrial Hemp (Cannabis sativa L.) Using Artificial Intelligence Methods

by Dominika Sieracka, Maciej Zaborowicz and Jakub Frankowski

Agriculture 2023, 13(5), 1097; https://doi.org/10.3390/agriculture13051097 - 20 May 2023

Viewed by 2098

Abstract

Currently, there is a significant increase in interest in hemp cultivation and hemp products around the world. The hemp industry is a strongly developing branch of the economies of many countries. Short-term forecasting of the hemp seed and grain yield will provide growers [...] Read more.

Currently, there is a significant increase in interest in hemp cultivation and hemp products around the world. The hemp industry is a strongly developing branch of the economies of many countries. Short-term forecasting of the hemp seed and grain yield will provide growers and processors with information useful to plan the demand for employees, technical facilities (including appropriately sized drying houses and crop cleaning lines) and means of transport. This will help to optimize inputs and, as a result, increase the income from cultivation. One of the methods of yield prediction is the use of artificial intelligence (AI) methods. Neural modeling proved to be useful in predicting the yield of many plants, which is why work was undertaken to use it also to predict hemp yield. The research was carried out on selected, popular hemp varieties—Białobrzeskie and Henola. Their aim was to identify characteristic factors: climatic, cultivation and agrotechnical, affecting the size and quality of the yield. The collected data allowed the generation of Artificial Neural Network (ANN) models. It has been shown that based on a set of characteristics obtained during the cultivation process, it is possible to create a predictive neural model. Modeling using one output variable, which is seed yield, can be used in short-time prediction of industrial crops, which are gaining more and more importance. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

10 pages, 836 KiB

Open AccessArticle

Agent-Based Modelling to Improve Beef Production from Dairy Cattle: Young Beef Production

by Addisu H. Addis, Hugh T. Blair, Paul R. Kenyon, Stephen T. Morris, Nicola M. Schreurs and Dorian J. Garrick

Agriculture 2023, 13(4), 898; https://doi.org/10.3390/agriculture13040898 - 19 Apr 2023

Cited by 1 | Viewed by 1458

Abstract

Approximately 42% of the total calves born in New Zealand’s dairy industry are either euthanized on farms or commercially slaughtered as so-called bobby calves within 2 weeks of age. These practices have perceived ethical issues and are considered a waste of resources because [...] Read more.

Approximately 42% of the total calves born in New Zealand’s dairy industry are either euthanized on farms or commercially slaughtered as so-called bobby calves within 2 weeks of age. These practices have perceived ethical issues and are considered a waste of resources because these calves could be grown on and processed for beef. Young beef cattle harvested between 8 and 12 months of age would represent a new class of beef production for New Zealand and would allow for a greater number of calves to be utilized for beef production, reducing bobby calf numbers in New Zealand. However, the acceptance of such a system in competition with existing sheep and beef cattle production systems is unknown. Therefore, the current study employed an agent-based model (ABM) developed for dairy-origin beef cattle production systems to understand price levers that might influence the acceptance of young beef production systems on sheep and beef cattle farms in New Zealand. The agents of the model were the rearer, finisher, and processor. Rearers bought in 4-days old dairy-origin calves and weaned them at approximately 100 kg live weight before selling them to finishers. Finishers managed the young beef cattle until they were between 8 and 12 months of age in contrast to 20 to 30 months for traditional beef cattle. Processing young beef cattle in existing beef production systems without any price premium only led to an additional 5% of cattle being utilized compared to the traditional beef cattle production system in New Zealand. This increased another 2% when both weaner cattle and young beef were sold at a price premium of 10%. In this scenario, Holstein Friesian young bull contributed more than 65% of total young beef cattle. Further premium prices for young beef cattle production systems increased the proportion of young beef cattle (mainly as young bull beef), however, there was a decrease in the total number of dairy-origin cattle processed, for the given feed supply, compared to the 10% premium price. Further studies are required to identify price levers and other alternative young beef production systems to increase the number of young beef cattle as well the total number of dairy-origin beef cattle for beef on sheep and beef cattle farms. Some potential options for investigation are meat quality, retailer and consumer perspectives, and whether dairy farmers may have to pay calf rearers to utilize calves with lower growth potential. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

18 pages, 4036 KiB

Open AccessArticle

EfficientPNet—An Optimized and Efficient Deep Learning Approach for Classifying Disease of Potato Plant Leaves

by Tahira Nazir, Muhammad Munwar Iqbal, Sohail Jabbar, Ayyaz Hussain and Mubarak Albathan

Agriculture 2023, 13(4), 841; https://doi.org/10.3390/agriculture13040841 - 09 Apr 2023

Cited by 4 | Viewed by 2093

Abstract

The potato plant is amongst the most significant vegetable crops farmed worldwide. The output of potato crop production is significantly reduced by various leaf diseases, which poses a danger to the world’s agricultural production in terms of both volume and quality. The two [...] Read more.

The potato plant is amongst the most significant vegetable crops farmed worldwide. The output of potato crop production is significantly reduced by various leaf diseases, which poses a danger to the world’s agricultural production in terms of both volume and quality. The two most destructive foliar infections for potato plants are early and late blight triggered by Alternaria solani and Phytophthora infestans. In actuality, farm owners predict these problems by focusing primarily on the alteration in the color of the potato leaves, which is typically problematic owing to uncertainty and significant time commitment. In these circumstances, it is vital to develop computer-aided techniques that automatically identify these disorders quickly and reliably, even in their early stages. This paper aims to provide an effective solution to recognize the various types of potato diseases by presenting a deep learning (DL) approach called EfficientPNet. More specifically, we introduce an end-to-end training-oriented approach by using the EfficientNet-V2 network to recognize various potato leaf disorders. A spatial-channel attention method is introduced to concentrate on the damaged areas and enhance the approach’s recognition ability to effectively identify numerous infections. To address the problem of class-imbalanced samples and to improve network generalization ability, the EANet model is tuned using transfer learning, and dense layers are added at the end of the model structure to enhance the feature selection power of the model. The model is tested on an open and challenging dataset called PlantVillage, containing images taken in diverse and complicated background conditions, including various lightning conditions and the different color changes in leaves. The model obtains an accuracy of 98.12% on the task of classifying various potato plant leaf diseases such as late blight, early blight, and healthy leaves in 10,800 images. We have confirmed through the performed experiments that our approach is effective for potato plant leaf disease classification and can robustly tackle distorted samples. Hence, farmers can save money and harvest by using the EfficientPNet tool. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

13 pages, 2555 KiB

Open AccessArticle

EffiMob-Net: A Deep Learning-Based Hybrid Model for Detection and Identification of Tomato Diseases Using Leaf Images

by Zahid Ullah, Najah Alsubaie, Mona Jamjoom, Samah H. Alajmani and Farrukh Saleem

Agriculture 2023, 13(3), 737; https://doi.org/10.3390/agriculture13030737 - 22 Mar 2023

Cited by 13 | Viewed by 2709

Abstract

As tomatoes are the most consumed vegetable in the world, production should be increased to fulfill the vast demand for this vegetable. Global warming, climate changes, and other significant factors, including pests, badly affect tomato plants and cause various diseases that ultimately affect [...] Read more.

As tomatoes are the most consumed vegetable in the world, production should be increased to fulfill the vast demand for this vegetable. Global warming, climate changes, and other significant factors, including pests, badly affect tomato plants and cause various diseases that ultimately affect the production of this vegetable. Several strategies and techniques have been adopted for detecting and averting such diseases to ensure the survival of tomato plants. Recently, the application of artificial intelligence (AI) has significantly contributed to agronomy in the detection of tomato plant diseases through leaf images. Deep learning (DL)-based techniques have been largely utilized for detecting tomato leaf diseases. This paper proposes a hybrid DL-based approach for detecting tomato plant diseases through leaf images. To accomplish the task, this study presents the fusion of two pretrained models, namely, EfficientNetB3 and MobileNet (referred to as the EffiMob-Net model) to detect tomato leaf diseases accurately. In addition, model overfitting was handled using various techniques, such as regularization, dropout, and batch normalization (BN). Hyperparameter tuning was performed to choose the optimal parameters for building the best-fitting model. The proposed hybrid EffiMob-Net model was tested on a plant village dataset containing tomato leaf disease and healthy images. This hybrid model was evaluated based on the best classifier with respect to accuracy metrics selected for detecting the diseases. The success rate of the proposed hybrid model for accurately detecting tomato leaf diseases reached 99.92%, demonstrating the model’s ability to extract features accurately. This finding shows the reliability of the proposed hybrid model as an automatic detector for tomato plant diseases that can significantly contribute to providing better solutions for detecting other crop diseases in the field of agriculture. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

22 pages, 2962 KiB

Open AccessArticle

A Hybrid Framework for Detection and Analysis of Leaf Blight Using Guava Leaves Imaging

by Sidrah Mumtaz, Mudassar Raza, Ofonime Dominic Okon, Saeed Ur Rehman, Adham E. Ragab and Hafiz Tayyab Rauf

Agriculture 2023, 13(3), 667; https://doi.org/10.3390/agriculture13030667 - 13 Mar 2023

Cited by 4 | Viewed by 1436

Abstract

Fruit is an essential element of human life and a significant gain for the agriculture sector. Guava is a common fruit found in different countries. It is considered the fourth primary fruit in Pakistan. Several bacterial and fungal diseases found in guava fruit [...] Read more.

Fruit is an essential element of human life and a significant gain for the agriculture sector. Guava is a common fruit found in different countries. It is considered the fourth primary fruit in Pakistan. Several bacterial and fungal diseases found in guava fruit decrease production daily. Leaf Blight is a common disease found in guava fruit that affects the growth and production of fruit. Automatic detection of leaf blight disease in guava fruit can help avoid decreases in its production. In this research, we proposed a CNN-based deep model named SidNet. The proposed model contains thirty-three layers. We used a guava dataset for early recognition of leaf blight, which consists of two classes. Initially, the YCbCr color space was employed as a preprocessing step in detecting leaf blight. As the original dataset was small, data augmentation was performed. DarkNet-53, AlexNet, and the proposed SidNet were used for feature acquisition. The features were fused to get the best-desired results. Binary Gray Wolf Optimization (BGWO) was used on the fused features for feature selection. The optimized features were given to the variants of SVM and KNN classifiers for classification. The experiments were performed on 5- and 10-fold cross validation. The highest achievable outcomes were 98.9% with 5-fold and 99.2% with 10-fold cross validation, confirming the evidence that the identification of Leaf Blight is accurate, successful, and efficient. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

15 pages, 7444 KiB

Open AccessArticle

Pest Localization Using YOLOv5 and Classification Based on Quantum Convolutional Network

by Javeria Amin, Muhammad Almas Anjum, Rida Zahra, Muhammad Imran Sharif, Seifedine Kadry and Lukas Sevcik

Agriculture 2023, 13(3), 662; https://doi.org/10.3390/agriculture13030662 - 13 Mar 2023

Cited by 8 | Viewed by 2304

Abstract

Pests are always the main source of field damage and severe crop output losses in agriculture. Currently, manually classifying and counting pests is time consuming, and enumeration of population accuracy might be affected by a variety of subjective measures. Additionally, due to pests’ [...] Read more.

Pests are always the main source of field damage and severe crop output losses in agriculture. Currently, manually classifying and counting pests is time consuming, and enumeration of population accuracy might be affected by a variety of subjective measures. Additionally, due to pests’ various scales and behaviors, the current pest localization algorithms based on CNN are unsuitable for effective pest management in agriculture. To overcome the existing challenges, in this study, a method is developed for the localization and classification of pests. For localization purposes, the YOLOv5 is trained using the optimal learning hyperparameters which more accurately localize the pest region in plant images with 0.93 F1 scores. After localization, pest images are classified into Paddy with pest/Paddy without pest using the proposed quantum machine learning model, which consists of fifteen layers with two-qubit nodes. The proposed network is trained from scratch with optimal parameters that provide 99.9% classification accuracy. The achieved results are compared to the existing recent methods, which are performed on the same datasets to prove the novelty of the developed model. Full article

(This article belongs to the Special Issue Big Data Analytics and Machine Learning for Smart Agriculture)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Big Data Analytics and Machine Learning for Smart Agriculture

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI