Cargando…
Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches
Accurate information about growing crops allows for regulating the internal stocks of agricultural products and drawing strategies for negotiating agricultural commodities on financial markets. Machine learning methods are widely implemented for crop type recognition and classification based on sate...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695680/ https://www.ncbi.nlm.nih.gov/pubmed/36433199 http://dx.doi.org/10.3390/s22228600 |
_version_ | 1784838122706567168 |
---|---|
author | Matvienko, Ivan Gasanov, Mikhail Petrovskaia, Anna Kuznetsov, Maxim Jana, Raghavendra Pukalchik, Maria Oseledets, Ivan |
author_facet | Matvienko, Ivan Gasanov, Mikhail Petrovskaia, Anna Kuznetsov, Maxim Jana, Raghavendra Pukalchik, Maria Oseledets, Ivan |
author_sort | Matvienko, Ivan |
collection | PubMed |
description | Accurate information about growing crops allows for regulating the internal stocks of agricultural products and drawing strategies for negotiating agricultural commodities on financial markets. Machine learning methods are widely implemented for crop type recognition and classification based on satellite images. However, field classification is complicated by class imbalance and aggregation of pixel-wise into field-wise forecasting. We propose here a Bayesian methodology for the aggregation of classification results. We report the comparison of class balancing techniques. We also report the comparison of classical machine learning methods and the U-Net convolutional neural network for classifying crops using a single satellite image. The best result for single-satellite-image crop classification was achieved with an overall accuracy of 77.4% and a Macro F1-score of 0.66. Bayesian aggregation for field-wise classification improved the result obtained using majority voting aggregation by 1.5%. We demonstrate here that the Bayesian aggregation approach outperforms the majority voting and averaging strategy in overall accuracy for the single-image crop classification task. |
format | Online Article Text |
id | pubmed-9695680 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96956802022-11-26 Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches Matvienko, Ivan Gasanov, Mikhail Petrovskaia, Anna Kuznetsov, Maxim Jana, Raghavendra Pukalchik, Maria Oseledets, Ivan Sensors (Basel) Article Accurate information about growing crops allows for regulating the internal stocks of agricultural products and drawing strategies for negotiating agricultural commodities on financial markets. Machine learning methods are widely implemented for crop type recognition and classification based on satellite images. However, field classification is complicated by class imbalance and aggregation of pixel-wise into field-wise forecasting. We propose here a Bayesian methodology for the aggregation of classification results. We report the comparison of class balancing techniques. We also report the comparison of classical machine learning methods and the U-Net convolutional neural network for classifying crops using a single satellite image. The best result for single-satellite-image crop classification was achieved with an overall accuracy of 77.4% and a Macro F1-score of 0.66. Bayesian aggregation for field-wise classification improved the result obtained using majority voting aggregation by 1.5%. We demonstrate here that the Bayesian aggregation approach outperforms the majority voting and averaging strategy in overall accuracy for the single-image crop classification task. MDPI 2022-11-08 /pmc/articles/PMC9695680/ /pubmed/36433199 http://dx.doi.org/10.3390/s22228600 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Matvienko, Ivan Gasanov, Mikhail Petrovskaia, Anna Kuznetsov, Maxim Jana, Raghavendra Pukalchik, Maria Oseledets, Ivan Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title | Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title_full | Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title_fullStr | Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title_full_unstemmed | Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title_short | Bayesian Aggregation Improves Traditional Single-Image Crop Classification Approaches |
title_sort | bayesian aggregation improves traditional single-image crop classification approaches |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9695680/ https://www.ncbi.nlm.nih.gov/pubmed/36433199 http://dx.doi.org/10.3390/s22228600 |
work_keys_str_mv | AT matvienkoivan bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT gasanovmikhail bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT petrovskaiaanna bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT kuznetsovmaxim bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT janaraghavendra bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT pukalchikmaria bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches AT oseledetsivan bayesianaggregationimprovestraditionalsingleimagecropclassificationapproaches |