Authors:
S. Rubin Bose, R. Regin, J. Angelin Jeba, S. Suman Rajest, Sayyed Khawar Abbas

Addresses:
School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A Engineering College, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Information Systems, Corvinus University of Budapest, Budapest, Hungary.

Abstract:

This study proposes a novel approach to classify and cluster soil images by combining Convolutional Neural Networks (CNNs) with hybrid feature extraction techniques. The system employs CNN for supervised soil classification and integrates colour histograms, texture features with Haralick descriptors, and CNN-based features for unsupervised clustering. Experimental results demonstrate the effectiveness of the proposed method in accurately categorising and grouping soil types, underscoring its potential to enhance soil nutrient assessment and monitoring systems. By analysing soil image data, the proposed system effectively identifies different soil classes and clusters, assisting in soil health evaluation. The study explores various algorithms, evaluates their performance, and highlights the potential applications in precision agriculture and sustainable farming. This study explores the application of machine learning and computer vision to soil analysis, offering rapid, non-destructive assessment methods that support better agricultural decision-making. Additionally, they provide valuable information on soil conditions to optimise crop management. The integration of advanced analytics and AI promises improved accuracy and scalability. Future work should focus on integrating nutrient prediction, yield estimation, multi-sensor data fusion, and real-time soil monitoring. Enhancing model generalisation, efficiency, and integration with smart farming technologies is also a vital consideration. 

Keywords: Precision Agriculture; Soil Image Classification; Convolutional Neural Network; Nutrient Assessment; Computer Vision; Agricultural Decision-Making; Yield Estimation.

Received on: 02/11/2024, Revised on: 06/01/2025, Accepted on: 28/02/2025, Published on: 14/09/2025

DOI: 10.69888/FTSESS.2025.000541

FMDB Transactions on Sustainable Environmental Sciences, 2025 Vol. 2 No. 3, Pages: 151-160

• Views : 87
• Downloads : 13

Download PDF