Spatial Assessment of Crop Water Stress and Yield Management Zones in Irrigated Wheat and Potato Using Thermal Imaging, Remote Sensing and Machine Learning

Water scarcity is one of the major challenges facing sustainable agriculture in arid regions, such as Saudi Arabia, where crop production relies heavily on groundwater irrigation. This study aimed to assess the spatial dynamics of crop water stress and yield for the delineation of management zones for irrigated wheat (Triticum aestivum L.) and potato (Solanum tuberosum L.) crops grown in the hyper-arid conditions of the Wadi-Ad-Dawasir region in Saudi Arabia. An integrated framework was developed by combining thermal imaging, Sentinel-2 satellite data, and machine learning techniques (RF and XGBoost) to evaluate the crop water stress, and yield for the delineation of yield management zones. Ground-based thermal imagery and meteorological observations were used to determine the Crop Water Stress Index (CWSI), while Sentinel-2-derived vegetation indices were employed to map water stress across the experimental fields. Results showed that the potato fields maintained larger non-stressed areas (69–73%) compared to wheat fields (32–45%). Furthermore, the potato crop achieved higher yields (56.3–62.0 t ha−1) and higher water use efficiency (WUE) values of 6.61 kg m−3 (based on crop water requirements, ETc) and 11.56 kg m−3 (based on applied water), compared to the wheat crop which had WUE values of 0.474 and 0.650 kg m−3, respectively. Unlike conventional approaches that rely on single-source data, this study highlights the added value of integrating thermal information with satellite-derived spectral indices to improve the detection of water stress and its impact on crop productivity. These findings offer new insights into precision irrigation management and support the development of scalable decision-making tools, thereby contributing to sustainable agricultural production in water-scarce regions.

Authors

Institutions

Publication Details

Journal
Agriculture
Published
2026-11-19
DOI
https://doi.org/10.3390/agriculture16222555
Primary Topic
Remote Sensing in Agriculture
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Spatial Assessment of Crop Water Stress and Yield Management Zones in Irrigated Wheat and Potato Using Thermal Imaging, Remote Sensing and Machine Learning

ElKamil Tola, David J. MULLA, Rangaswamy Madugundu, Khalid A. Al‐Gaadi et al.
Agriculture
Remote Sensing in Agriculture
article

Spatial Assessment of Crop Water Stress and Yield Management Zones in Irrigated Wheat and Potato Using Thermal Imaging, Remote Sensing and Machine Learning

ElKamil Tola, David J. MULLA, Rangaswamy Madugundu, Khalid A. Al‐Gaadi, Fahad Al-Aseery, Amr Shakir
article en

Abstract

Water scarcity is one of the major challenges facing sustainable agriculture in arid regions, such as Saudi Arabia, where crop production relies heavily on groundwater irrigation. This study aimed to assess the spatial dynamics of crop water stress and yield for the delineation of management zones for irrigated wheat (Triticum aestivum L.) and potato (Solanum tuberosum L.) crops grown in the hyper-arid conditions of the Wadi-Ad-Dawasir region in Saudi Arabia. An integrated framework was developed by combining thermal imaging, Sentinel-2 satellite data, and machine learning techniques (RF and XGBoost) to evaluate the crop water stress, and yield for the delineation of yield management zones. Ground-based thermal imagery and meteorological observations were used to determine the Crop Water Stress Index (CWSI), while Sentinel-2-derived vegetation indices were employed to map water stress across the experimental fields. Results showed that the potato fields maintained larger non-stressed areas (69–73%) compared to wheat fields (32–45%). Furthermore, the potato crop achieved higher yields (56.3–62.0 t ha−1) and higher water use efficiency (WUE) values of 6.61 kg m−3 (based on crop water requirements, ETc) and 11.56 kg m−3 (based on applied water), compared to the wheat crop which had WUE values of 0.474 and 0.650 kg m−3, respectively. Unlike conventional approaches that rely on single-source data, this study highlights the added value of integrating thermal information with satellite-derived spectral indices to improve the detection of water stress and its impact on crop productivity. These findings offer new insights into precision irrigation management and support the development of scalable decision-making tools, thereby contributing to sustainable agricultural production in water-scarce regions.

AgricultureVol. 16(22)
University of Minnesota (US), King Saud University (SA)
Remote Sensing in Agriculture
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon