{"title":"Deep learning for broadleaf weed seedlings classification incorporating data variability and model flexibility across two contrasting environments","authors":"Lorenzo León , Cristóbal Campos , Juan Hirzel","doi":"10.1016/j.aiia.2024.03.002","DOIUrl":null,"url":null,"abstract":"<div><p>The increasing deployment of deep learning models for distinguishing weeds and crops has witnessed notable strides in agricultural scenarios. However, a conspicuous gap endures in the literature concerning the training and testing of models across disparate environmental conditions. Predominant methodologies either delineate a single dataset distribution into training, validation, and testing subsets or merge datasets from diverse conditions or distributions before their division into the subsets. Our study aims to ameliorate this gap by extending to several broadleaf weed categories across varied distributions, evaluating the impact of training convolutional neural networks on datasets specific to particular conditions or distributions, and assessing their performance in entirely distinct settings through three experiments. By evaluating diverse network architectures and training approaches (<em>finetuning</em> versus <em>feature extraction</em>), testing various architectures, employing different training strategies, and amalgamating data, we devised straightforward guidelines to ensure the model's deployability in contrasting environments with sustained precision and accuracy.</p><p>In Experiment 1, conducted in a uniform environment, accuracy ranged from 80% to 100% across all models and training strategies, with <em>finetune</em> mode achieving a superior performance of 94% to 99.9% compared to the <em>feature extraction</em> mode at 80% to 92.96%. Experiment 2 underscored a significant performance decline, with accuracy figures between 25% and 60%, primarily at 40%, when the origin of the test data deviated from the train and validation sets. Experiment 3, spotlighting dataset and distribution amalgamation, yielded promising accuracy metrics, notably a peak of 99.6% for ResNet in <em>finetuning</em> mode to a low of 69.9% for InceptionV3 in <em>feature extraction</em> mode. These pivotal findings emphasize that merging data from diverse distributions, coupled with <em>finetuned</em> training on advanced architectures like ResNet and MobileNet, markedly enhances performance, contrasting with the relatively lower performance exhibited by simpler networks like AlexNet. Our results suggest that embracing data diversity and flexible training methodologies are crucial for optimizing weed classification models when disparate data distributions are available. This study gives a practical alternative for treating diverse datasets with real-world agricultural variances.</p></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":null,"pages":null},"PeriodicalIF":8.2000,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589721724000059/pdfft?md5=d8051b8dea55cec53a6ba7889cbc0c03&pid=1-s2.0-S2589721724000059-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Agriculture","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589721724000059","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The increasing deployment of deep learning models for distinguishing weeds and crops has witnessed notable strides in agricultural scenarios. However, a conspicuous gap endures in the literature concerning the training and testing of models across disparate environmental conditions. Predominant methodologies either delineate a single dataset distribution into training, validation, and testing subsets or merge datasets from diverse conditions or distributions before their division into the subsets. Our study aims to ameliorate this gap by extending to several broadleaf weed categories across varied distributions, evaluating the impact of training convolutional neural networks on datasets specific to particular conditions or distributions, and assessing their performance in entirely distinct settings through three experiments. By evaluating diverse network architectures and training approaches (finetuning versus feature extraction), testing various architectures, employing different training strategies, and amalgamating data, we devised straightforward guidelines to ensure the model's deployability in contrasting environments with sustained precision and accuracy.
In Experiment 1, conducted in a uniform environment, accuracy ranged from 80% to 100% across all models and training strategies, with finetune mode achieving a superior performance of 94% to 99.9% compared to the feature extraction mode at 80% to 92.96%. Experiment 2 underscored a significant performance decline, with accuracy figures between 25% and 60%, primarily at 40%, when the origin of the test data deviated from the train and validation sets. Experiment 3, spotlighting dataset and distribution amalgamation, yielded promising accuracy metrics, notably a peak of 99.6% for ResNet in finetuning mode to a low of 69.9% for InceptionV3 in feature extraction mode. These pivotal findings emphasize that merging data from diverse distributions, coupled with finetuned training on advanced architectures like ResNet and MobileNet, markedly enhances performance, contrasting with the relatively lower performance exhibited by simpler networks like AlexNet. Our results suggest that embracing data diversity and flexible training methodologies are crucial for optimizing weed classification models when disparate data distributions are available. This study gives a practical alternative for treating diverse datasets with real-world agricultural variances.