Satellite Soil Moisture Data-Driven to Predict Paddy Production Using Machine Learning Approach

Abstract

Measuring and mapping how wet the soil is accurately are very important for farming in a sustainable way, managing water resources, and studying the climate. On top of that, it also important to find out that, based on soil moisture of a land, what could be the potential paddy production. This study aims to explore the mapping of soil moisture of Rajshahi district in Bangladesh using multi-spectral remote-sensing satellite images and based on historical paddy production data, what could be the possible paddy production in the year 2025. To find out the possible production in the year of 2025, I have used the Machine Learning techniques to predict the paddy production based on the data generated from the soil moisture map and integrated the data with the paddy production statistics data of Bangladesh Bureau of Statistics (BBS). A total of 14 Landsat scenes covers the entire Rajshahi district. Thus, a set of Landsat imagery (a total of 14 scenes) for the year 2017, 2020 and 2023 was used in this study to map the soil moisture of Bangladesh through the application of Geographical Information System (GIS) and Remote Sensing. Satellite Image preprocessing, correction, and analysis were done with the ArcGIS software (version 10.8, developed by Environmental Systems Research Institute, USA) and prediction was found out through Google Colab. The map in this study indicates the level of soil wetness in Rajshahi, ranging from Very Dry, Dry, Wet to Very Wet soils. Based upon the study, it is found out that, it is possible to increase paddy production rate by 47.95% in the year 2025 due to improvement of soil moisture conditions.

Introduction

This study examines how soil moisture influences paddy production in Rajshahi, Bangladesh, utilizing GIS and remote sensing techniques, particularly Landsat 8 satellite images from 2017, 2020, and 2023. It maps soil moisture levels, showing improvements over time, and predicts a 47.95% increase in paddy production by 2025 using machine learning and Bangladesh Bureau of Statistics (BBS) data. The research highlights the seasonal variability of soil moisture, with low moisture and paddy yields in the dry (aus) season and higher levels during the rainy season.

Previous studies have mapped soil moisture across Bangladesh with high accuracy, aiding agricultural and environmental planning. However, these studies lacked detailed predictions for paddy production specific to Rajshahi. This research fills that gap by linking temporal soil moisture data with paddy yield predictions.

The methodology includes downloading and preprocessing multispectral Landsat 8 images, applying radiometric and atmospheric corrections, and using Principal Component Analysis (PCA) to select key spectral bands (Band 5 - NIR and Band 6 - SWIR) for soil moisture estimation. GIS software (ArcMap) and remote sensing tools (ENVI) are used for spatial analysis.

The study also reviews related work on machine learning techniques for soil moisture and crop yield prediction, emphasizing the role of advanced ML models (e.g., neural networks, random forests) in improving prediction accuracy. Overall, the project provides a reliable soil moisture map and an early paddy production forecast to support sustainable agriculture and resource management in the Rajshahi region.

Conclusion

This work shows how LANDSAT 8 OLI/TIRS satellite image can be used to study soil moisture, which is very important for disaster prediction, environmental monitoring, and hydro-logical applications. Data from Remote Sensing (RS) have helped to improve electronic land modeling on different scales in recent years. This study also shows that Landsat 8 OLI/TIRS images can measure soil moisture of Bangladesh. The study uses the Geographic Information System (GIS) technique, a powerful tool that improves the accuracy of soil moisture and land use mapping by studying remote sensing data. This study also uses high spatial resolution satellite (Landsat 8 data) to map the soil moisture and give correct and detailed soil moisture information that is up to date. The results of this study show that multi-spectral remote sensing satellite imagery can map soil moisture well at a regional scale. The study also combines satellite data with ground measurements and advanced modeling techniques to make the soil moisture estimates more accurate and reliable. The method used in this study can be used in other places with similar environmental features to watch and control soil moisture levels well. Finally, LANDSAT 8 satellite data and GIS technique is used to map Soil Moisture in Rajshahi district and evaluates the potential paddy production rate. We have also found out yearly increase of soil moisture quality level (Wet Level). There could be an increasing number of potential paddy production in 2025 by 47.95%.

References

[1] M. M. B. W. A. W. M. M. H. Md. Mamun Hossain, Asswad Sarker Noman and A. S. M. Miah, “Exploring Bangladesh’s soil moisture dynamics via multispectral remote sensing satellite image,” 2023. [2] “Bangladesh bureau of statistics,” https://bbs.gov.bd/site/page/3e838eb6-30a2-4709-be85-40484b0c16c6/Yearbook-of-Agricultural-Statistics. [3] “Earth explorer,” Earth Explorer: https://earthexplorer.usgs.gov/. [4] “Normalized difference water index,” https://eos.com/make-an-analysis/ndwi. [5] Z. K. Zhihao Hong and R. Iyer, “A data-driven approach to soil moisture collection and prediction using a wireless sensor network and machine learning techniques,” 978-1-5090-0898-8/16/31.002016IEEE, 2016. [6] A. L. M. D. Umesh Acharya and P. G. Oduor, “Machine learning for predicting field soil moisture using soil, crop and nearby weather station data in the red river valley of the north,” https://doi.org/10.3390/soilsystems5040057, 2021. [7] X. Z. L. Z. X. X. Yu Cai, Wengang ZhengID, “Research on soil moisture prediction model based on deep learning,” https://doi.org/10.1371/journal.pone.0214508, 2019. [8] P. G. ABHINAV SHARMA, ARPIT JAIN and V. CHOWDARY, “Machine learning applications for precision agriculture: A comprehensive review,” Digital Object Identifier 10.1109/ACCESS.2020.3048415, 2020. [9] R. Elashmawy and I. Uysal, “Precision agriculture using soil sensor driven machine learning for smart strawberry production,” MDPI, 2023. [10] O. J. M. Aniruddha Basak, Kevin M. Schmidt, “From data to interpretable models: machine learning for soil moisture forecasting,” International Journal of Data Science and Analytics, 2023. [11] D. I. Fabrizio Balducci and G. Pirlo, “Machine learning applications on agricultural datasets for smart farm enhancement,” Machines 2018, 6, 38; doi:10.3390/machines6030038, 2018. [12] “Geodesh,” http://data.gov.bd/dataset/geodash. [13] “Python library,” https://docs.python.org/3/library/index.html. [14] “ML library,” https://scikit-learn.org/stable/index.html.

Copyright

Copyright © 2025 Rebina Ferdous, Md Mehedi Imam, Md. Hafizur Rahman. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.