Automated Farm Ponds Detection using Satellite Imagery and Deep Learning: Insights from Kadwanchi village, Maharashtra
DOI:
https://doi.org/10.58825/jog.2025.19.1.220Keywords:
Deep Learning, , remote sensing, Satellite data, ArcGIS, Geographic Information System (GIS)Abstract
Farm ponds play a crucial role in rainwater harvesting and irrigation, making their accurate detection essential for effective water resource management. This study explores the application of deep learning models for detecting farm ponds in Kadwanchi village, Maharashtra, where water scarcity challenges agricultural productivity. Using satellite imagery, the study compares and evaluates four deep learning models—U-Net, Mask RCNN, DeepLabV3+, and Feature Classifier—based on precision, recall, and F1 score. The Feature Classifier emerged as the most accurate model, achieving a perfect precision score of 1.0, a recall of 0.863, and an F1 score of 0.927, detecting 296 farm ponds. U-Net also performed well, with an F1 score of 0.873, while Mask RCNN and DeepLabV3+ showed more moderate results. These findings can assist government agencies in making data-driven decisions about water resource management and promoting sustainable agriculture in water-scarce regions. Future research could focus on hybrid models and larger datasets to improve farm pond detection accuracy.
References
Bali, S., Gupta, M., & Sharma, S. (2023). Advances in remote sensing for precision agriculture: A review. Remote Sensing Applications: Society and Environment, 31, 100858. https://doi.org/10.1016/j.rsase.2023.100858
Bandyopadhyay, K., Kumar, A., & Kaur, G. (2020). Impact of farm ponds on groundwater recharge and agricultural productivity: Evidence from Rajasthan, India. Water International, 45(5), 590-605. https://doi.org/10.1080/02508060.2020.1800014
Chen, L., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-8). https://doi.org/10.1109/CVPR.2017.1
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (pp. 2961-2969). https://doi.org/10.1109/ICCV.2017.322
Kaur, P., & Vatta, K. (2015). Challenges in mapping the area and volume of farm ponds for efficient water management. Journal of Soil and Water Conservation, 70(3), 85-91. https://doi.org/10.2489/jswc.70.3.85
Khan, A., Saleem, M., & Choudhary, A. (2021). Review of deep learning techniques for image segmentation in agriculture. Journal of Imaging, 7(10), 163. https://doi.org/10.3390/joi7100163
Nambiar, A. (2019). Discrepancies in volume estimation of farm ponds: The role of evaporation losses. Water Resources Management, 33(1), 25-33. https://doi.org/10.1007/s11269-018-2060-x
Reddy, K. P., Reddy, R. S., & Reddy, B. S. (2022). Farm pond as an effective water management practice in dryland agriculture: A case study from Andhra Pradesh, India. Agricultural Water Management, 253, 106914. https://doi.org/10.1016/j.agwat.2021.106914
Ronneberger, O., Fischer, P., & Becker, A. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention (pp. 234-241). https://doi.org/10.1007/978-3-319-24574-4_28
Shah, T. (2016). The challenge of siltation and volume estimation in farm ponds. International Journal of Water Resources Development, 32(4), 564-579. https://doi.org/10.1080/07900627.2016.1144050
Singh, R., & Jain, A. (2018). Integrating advanced technologies for farm pond area and volume mapping: Challenges and prospects. Journal of Hydrology, 556, 1009-1017. https://doi.org/10.1016/j.jhydrol.2018.09.071
Singh, R., & Singh, A. (2019). Water management practices in Indian agriculture: Challenges and opportunities. Indian Journal of Agricultural Sciences, 89(3), 477-487. https://doi.org/10.56093/ijas.v89i3.87383
Tiwari, A., Bhan, S., & Sinha, A. (2020). Object detection in agriculture using deep learning: A survey. Artificial Intelligence Review, 54(1), 1-25. https://doi.org/10.1007/s10462-020-09816-0
Zhang, Y., Chen, L., & Zhang, Q. (2020). A comprehensive review on deep learning for crop classification in remote sensing images. Remote Sensing of Environment, 238, 111430. https://doi.org/10.1016/j.rse.2019.111430
Zhang, Y., Chen, L., & Zhang, Q. (2020). A comprehensive review on deep learning for crop classification in remote sensing images. Remote Sensing of Environment, 238, 111430. https://doi.org/10.1016/j.rse.2019.111430
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Geomatics

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.