Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area
Climate change and water scarcity bring significant challenges to agricultural systems in the Mediterranean region. Novel methods are required to rapidly monitor the water stress of the crop to avoid qualitative losses of agricultural products. This study aimed to predict the stem water potential of...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/13/23/3325 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850106977563181056 |
|---|---|
| author | Simone Pietro Garofalo Anna Francesca Modugno Gabriele De Carolis Nicola Sanitate Mesele Negash Tesemma Giuseppe Scarascia-Mugnozza Yitagesu Tekle Tegegne Pasquale Campi |
| author_facet | Simone Pietro Garofalo Anna Francesca Modugno Gabriele De Carolis Nicola Sanitate Mesele Negash Tesemma Giuseppe Scarascia-Mugnozza Yitagesu Tekle Tegegne Pasquale Campi |
| author_sort | Simone Pietro Garofalo |
| collection | DOAJ |
| description | Climate change and water scarcity bring significant challenges to agricultural systems in the Mediterranean region. Novel methods are required to rapidly monitor the water stress of the crop to avoid qualitative losses of agricultural products. This study aimed to predict the stem water potential of cotton (<i>Gossypium hirsutum</i> L., 1763) using Sentinel-2 satellite imagery and machine learning techniques to enhance monitoring and management of cotton’s water status. The research was conducted in Rutigliano, Southern Italy, during the 2023 cotton growing season. Different machine learning algorithms, including random forest, support vector regression, and extreme gradient boosting, were evaluated using Sentinel-2 spectral bands as predictors. The models’ performance was assessed using R<sup>2</sup> and root mean square error (RMSE). Feature importance was analyzed using permutation importance and SHAP methods. The random forest model using Sentinel-2 bands’ reflectance as predictors showed the highest performance, with an R<sup>2</sup> of 0.75 (±0.07) and an RMSE of 0.11 (±0.02). XGBoost (R<sup>2</sup>: 0.73 ± 0.09, RMSE: 0.12 ± 0.02) and AdaBoost (R<sup>2</sup>: 0.67 ± 0.08, RMSE: 0.13 ± 0.02) followed in performance. Visible (blue and red) and red edge bands were identified as the most influential predictors. The trained RF model was used to model the seasonal trend of cotton’s stem water potential, detecting periods of acute and moderate water stress. This approach demonstrates the prospective for high-frequency, non-invasive monitoring of cotton’s water status, which could support smart irrigation strategies and improve water use efficiency in Mediterranean cotton production. |
| format | Article |
| id | doaj-art-7f2a9167f4ac424996d1c9e2f2edc453 |
| institution | OA Journals |
| issn | 2223-7747 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj-art-7f2a9167f4ac424996d1c9e2f2edc4532025-08-20T02:38:42ZengMDPI AGPlants2223-77472024-11-011323332510.3390/plants13233325Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean AreaSimone Pietro Garofalo0Anna Francesca Modugno1Gabriele De Carolis2Nicola Sanitate3Mesele Negash Tesemma4Giuseppe Scarascia-Mugnozza5Yitagesu Tekle Tegegne6Pasquale Campi7Council for Agricultural Research and Economics, Research Center for Agriculture and Environment, Via Celso Ulpiani, 5, 70125 Bari, ItalyCouncil for Agricultural Research and Economics, Research Center for Agriculture and Environment, Via Celso Ulpiani, 5, 70125 Bari, ItalyCouncil for Agricultural Research and Economics, Research Center for Agriculture and Environment, Via Celso Ulpiani, 5, 70125 Bari, ItalyCouncil for Agricultural Research and Economics, Research Center for Agriculture and Environment, Via Celso Ulpiani, 5, 70125 Bari, ItalyBiocities Facility, European Forest Institute, Via Manziana 30, 00189 Roma, ItalyBiocities Facility, European Forest Institute, Via Manziana 30, 00189 Roma, ItalyCircular Bioeconomy Alliance, 71 Queen Victoria Street, London EC4V 4BE, UKCouncil for Agricultural Research and Economics, Research Center for Agriculture and Environment, Via Celso Ulpiani, 5, 70125 Bari, ItalyClimate change and water scarcity bring significant challenges to agricultural systems in the Mediterranean region. Novel methods are required to rapidly monitor the water stress of the crop to avoid qualitative losses of agricultural products. This study aimed to predict the stem water potential of cotton (<i>Gossypium hirsutum</i> L., 1763) using Sentinel-2 satellite imagery and machine learning techniques to enhance monitoring and management of cotton’s water status. The research was conducted in Rutigliano, Southern Italy, during the 2023 cotton growing season. Different machine learning algorithms, including random forest, support vector regression, and extreme gradient boosting, were evaluated using Sentinel-2 spectral bands as predictors. The models’ performance was assessed using R<sup>2</sup> and root mean square error (RMSE). Feature importance was analyzed using permutation importance and SHAP methods. The random forest model using Sentinel-2 bands’ reflectance as predictors showed the highest performance, with an R<sup>2</sup> of 0.75 (±0.07) and an RMSE of 0.11 (±0.02). XGBoost (R<sup>2</sup>: 0.73 ± 0.09, RMSE: 0.12 ± 0.02) and AdaBoost (R<sup>2</sup>: 0.67 ± 0.08, RMSE: 0.13 ± 0.02) followed in performance. Visible (blue and red) and red edge bands were identified as the most influential predictors. The trained RF model was used to model the seasonal trend of cotton’s stem water potential, detecting periods of acute and moderate water stress. This approach demonstrates the prospective for high-frequency, non-invasive monitoring of cotton’s water status, which could support smart irrigation strategies and improve water use efficiency in Mediterranean cotton production.https://www.mdpi.com/2223-7747/13/23/3325drought stressGossypiummachine learningsatelliteremote sensingOptuna |
| spellingShingle | Simone Pietro Garofalo Anna Francesca Modugno Gabriele De Carolis Nicola Sanitate Mesele Negash Tesemma Giuseppe Scarascia-Mugnozza Yitagesu Tekle Tegegne Pasquale Campi Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area Plants drought stress Gossypium machine learning satellite remote sensing Optuna |
| title | Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area |
| title_full | Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area |
| title_fullStr | Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area |
| title_full_unstemmed | Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area |
| title_short | Explainable Artificial Intelligence to Predict the Water Status of Cotton (<i>Gossypium hirsutum</i> L., 1763) from Sentinel-2 Images in the Mediterranean Area |
| title_sort | explainable artificial intelligence to predict the water status of cotton i gossypium hirsutum i l 1763 from sentinel 2 images in the mediterranean area |
| topic | drought stress Gossypium machine learning satellite remote sensing Optuna |
| url | https://www.mdpi.com/2223-7747/13/23/3325 |
| work_keys_str_mv | AT simonepietrogarofalo explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT annafrancescamodugno explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT gabrieledecarolis explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT nicolasanitate explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT meselenegashtesemma explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT giuseppescarasciamugnozza explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT yitagesutekletegegne explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea AT pasqualecampi explainableartificialintelligencetopredictthewaterstatusofcottonigossypiumhirsutumil1763fromsentinel2imagesinthemediterraneanarea |