Citation

T., Gayathri Devi and A., Srinivasan and G, Rajkumar and Sakthivel, Sudha and Chuan, Lee Loo and Roslee, Mardeni (2025) AI-Based Decision Support System for Soil Conservation Using Convolutional and Recurrent Neural Networks. In: 11th International Conference on Engineering and Emerging Technologies, ICEET 2025, 22 October 2025 - 23 October 2025, Kuala Lumpur, Malaysia.

Text IEEE Xplore Full-Text PDF_10.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

Soil erosion is a major problem in Tamil Nadu, India's Eastern Coast Plains, resulting in degraded soil and lower agricultural yields. The proposed initiative will use two state-of-the-art deep learning techniques to develop a Decision Support System (DSS): Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Because this system is designed to stop soil erosion and maintain soil health, it is a helpful tool for farmers, researchers, and policymakers alike. The DSS will make data collected with remote sensing technologies available. Details about the soil, vegetation type, hills and valleys, climate, rainfall, and land cover will all be covered. The CNN model uses the remote sensing data to create features. The RNN model will perform forecasting of soil erosion trends on the basis of historical data such as rainfall and temperature. The merging of the CNN and RNN will produce a powerful and accurate model to predict soil erosion. Be upgraded deep learning algorithm will be developed to give more precise results and the DSS will also be user-friendly. Inputs: The inputs for the DSS can be derived from required parameters soil erosion possibility can be seen. And outputs: Reports. The DSS is designed to stop soil erosion and keep soil in good health. Finally, the developed Decision Support System (DSS) based on Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) can effectively predict soil erosion trends in the Tamil Nadu Eastern Coastal Plains, India. The DSS maintains the soil's health and stops soil erosion. Better crop yields and sustainable agriculture are the outcomes of this research.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Convolutional neural networks
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	20 Apr 2026 03:18
Last Modified:	20 Apr 2026 03:18
URII:	http://shdl.mmu.edu.my/id/eprint/15766

Downloads

Edit (login required)