EUVIMEDEUVIMED entdecken
Crossref

AI-Enabled Smart Irrigation and Crop Planning Framework for Water-Scarce Rural Regions Using Interpretable Machine Learning: A Case Study of Sabarkantha (Khedbrahma), Gujarat

Dr. Jayesh Gamar, Himaniben Gajjar

SPU - Journal of Science, Technology and Management Research · 01.07.2026 · 71-78

DOI: 10.63766/spujstmr.26.000074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SPU - Journal of Science, Technology and Management Research, online erschienen am 01.07.2026. Verfasst von Dr. Jayesh Gamar und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The depletion of safe and usable water for agriculture is one of the many escalating challenges that semi-arid regions face regarding the sustainability of their agricultural sector. This challenge is compounded by the dwindling supply of groundwater due to conventional irrigation systems throughout these regions. The irrigation systems in these areas rely heavily on heuristic decision-making, which can lead to poor use of water, groundwater depletion, and variable crop yields from year to year. This paper proposes the development of a smart irrigation and crop planning system that combines both machine learning and explainable artificial intelligence (XAI) to create transparent and data-driven agricultural decisions through AI-assisted irrigation and crop planning in the semi-arid region of Sabarkantha, Gujarat, India. The proposed solution to the depletion of groundwater relies on previous research that suggests that applying AI-assisted irrigation and crop planning can result in reduced water use while positively influencing agricultural productivity. The proposed AI-assisted irrigation and crop planning system will be assessed in the Khedbrahma sub-region of Sabarkantha, as demonstrated through a case study. The proposed system will utilize climatic factors, soil properties, groundwater information, and crop requirements to provide optimized irrigation recommendations along with recommended crops suitable for planting. The proposed system will incorporate interpretable models (i.e., Random Forest, XGBoost) and the calculated Shapley values to provide farmers with transparency and confidence in their decisions. The experimental results from the datasets for the region indicate the potential for 25 to 40 percent savings from their irrigation water use while ensuring or increasing crop yields. The proposed AI-assisted irrigation and crop planning system will also be cost-effective and scalable. Moreover, the proposed system will be well-matched to rural areas lacking the economic means to purchase or implement capital-intensive solutions.

Zitieren

APA

Gamar, D. J., & Gajjar, H. (2026). AI-Enabled Smart Irrigation and Crop Planning Framework for Water-Scarce Rural Regions Using Interpretable Machine Learning: A Case Study of Sabarkantha (Khedbrahma), Gujarat. SPU - Journal of Science, Technology and Management Research, 71-78. https://doi.org/10.63766/spujstmr.26.000074

Vancouver

Gamar DJ, Gajjar H. AI-Enabled Smart Irrigation and Crop Planning Framework for Water-Scarce Rural Regions Using Interpretable Machine Learning: A Case Study of Sabarkantha (Khedbrahma), Gujarat. SPU - Journal of Science, Technology and Management Research. 2026:71-78. doi:10.63766/spujstmr.26.000074

BibTeX
@article{Gamar2026,
  author = {Gamar, Dr. Jayesh and Gajjar, Himaniben},
  title = {AI-Enabled Smart Irrigation and Crop Planning Framework for Water-Scarce Rural Regions Using Interpretable Machine Learning: A Case Study of Sabarkantha (Khedbrahma), Gujarat},
  journal = {SPU - Journal of Science, Technology and Management Research},
  year = {2026},
  pages = {71--78},
  doi = {10.63766/spujstmr.26.000074}
}
Kostenlos starten →