Skip to content
Open access

An Explainable Hybrid Attention Based TabNet–BiLSTM Framework for Intelligent Soil Data-Driven Crop and Fertilizer Recommendation

Aug 2026 · International journal of computer information systems and industrial management applications · Vol 18, pp. 1359-1378 · 0 citations

TL;DR

The proposed AgriDeepFusion-XAI architecture provides a scalable, explainable, and reliable decision support system for an intelligent smart agricultural system.

Abstract

Accurate crop selection and fertilizer recommendation based on soil laboratory data analysis are essential for sustainable agriculture and precision nutrient management. Most existing crop recommendation systems lean on standalone machine learning or deep learning architectures that constrain their ability to model sparse feature relevance and contextual nutrient interactions simultaneously while keeping the model interpretable. We propose AgriDeepFusion-XAI, a hybrid deep learning architecture introduces a dual branch attention sequence fusion mechanism. It combines TabNet based sparse feature selection with BiLSTM based contextual representation learning then layers on explainable decision analysis through SHAP and LIME for intelligent crop classification and fertilizer recommendation. The TabNet branch carries out sequential attentive feature selection using sparsemax-based masking to identify the important soil attributes, while the BiLSTM branch learns the bidirectional dependencies hiding in soil feature sequences. Embeddings from both branches are fused through a dense integration layer to perform multi-class crop prediction which is followed by a rule guided fertilizer recommendation module. SHAP and LIME explainability techniques are integrated to enhance the interpretability which helps to provide global feature importance and instance-level explanations. The proposed architecture was evaluated using a seven years soil laboratory dataset collected from soil lab located in Madurai, Tamilnadu, India. It includes sixteen physiochemical soil attributes and twenty two crop categories. Data preprocessing pipeline included missing values handling, feature normalization, categorical encoding and stratified data partitioning. Model performance was evaluated through stratified five fold cross validation. Experimental results shows that AgriDeepFusion-XAI achieves 97.3% classification accuracy, 97.92% macro-F1 score, and 97.85% precision and 97% recall which outperforms standalone TabNet and BiLSTM models by 3-4%. The proposed AgriDeepFusion-XAI architecture provides a scalable, explainable, and reliable decision support system for an intelligent smart agricultural system.

Read PDF

Similar papers

Open access Oct 2026

AI-Based Crop Recommendation for Farmers and Farm Management System

Agricultural decision-making has historically depended on empirical intuition, localized traditional knowledge, and fragmented external advisories. Such manual heuristics frequently fail to account for dynamic soil chemistry, erratic microclimatic fluctuations, and volatile market conditions, leading to misallocated ag...

Malar K, B. T. Mithun, P. R et al. · 0 citations
Open access Oct 2026

A multimodal context-aware AI recommender for smart farming

Agricultural productivity in developing regions is significantly affected by plant diseases and pest infestations, making early detection and timely intervention essential for improving crop yield and food security. This study proposes a multimodal context-aware AI recommendation framework that integrates maize leaf im...

John Telesphory Mhagama, Kanwal Garg · 0 citations
Oct 2026

Hybrid Quantum Deep Learning and Machine Learning Framework for Soil Image Analysis with XGBoost-based Crop and Random Forest Fertilizer Recommendation

Farm productivity largely depends on soil conditions, choosing the right crops, and using fertilizers in a balanced way. This work presents a multi-stage, AI-driven decision support system that integrates quantum computing with classical machine learning, leveraging quantum circuits for increased feature representa...

C. Naik, Mamata Garanayak, Trilochan Rout et al. · 0 citations
Oct 2026

An Explainable Hybrid Deep Learning Model for Soil Fertility Classification and Sustainable Agricultural Recommendations

In agriculture, soil fertility has a significant impact on farmer welfare. Soil fertility is the primary factor that determines crop production. Climate change, water resources, soil nutrients, and other environmental elements affect the soil fertility. In real time, the process of evaluating soil fertility is challeng...

V. Prabhavathi, P. Kuppusamy · 0 citations
Conference Open access Oct 2026

Explainable AI-based Multilingual Crop Recommendation System for Precision Agriculture using Machine Learning

The problem of selecting crops using soil and environmental factors still poses challenges for precision agriculture. It directly impacts the performance of agricultural production, available resources, and the income of farmers. An intelligent multilingual crop recommendation system was developed using machine learnin...

S. Seetharamudu, S. Sameen, D. Anusha et al. · 0 citations
Oct 2026

A NOVEL HYBRID CLUSTERING AND ENSEMBLE LEARNING FRAMEWORK FOR AGRICULTURAL CROP RECOMMENDATION

Selecting a suitable crop for a given soil and climatic condition is an important decision-support task in precision agriculture. This paper investigates a hybrid data-mining framework that combines unsupervised clustering with ensemble classification for crop recommendation. The dataset contains 2,200 records, seven n...

S. R. Priya, K.Nirmala · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.