Climate-Aware Multimodal Deep Learning Framework for Banana Leaf Disease Recognition Using CNN-Based Image and Environmental Feature Fusion

Abstract

Banana cultivation in Maharashtra, particularly in the Jalgaon district, is severely affected by foliar diseases that significantly reduce crop productivity and quality. Traditional disease diagnosis methods rely heavily on manual inspection and expert intervention, which are often limited in rural agricultural regions. Moreover, existing deep learning-based disease detection systems primarily depend on visual image features while overlooking the influence of environmental conditions on disease progression. This study aimed to develop a climate-aware intelligent framework for accurate and context-sensitive banana leaf disease identification. The proposed framework integrates convolutional neural network (CNN)-based image analysis with agro-climatic parameters, including temperature, humidity and precipitation. A region-specific dataset containing approximately 18,000 banana leaf images representing nine disease categories was developed using field-level image acquisition and augmentation techniques. In parallel, long-term meteorological data collected from the Jalgaon region were incorporated to capture environmental conditions associated with disease occurrence. The CNN-extracted visual feature vector was fused with climate feature vectors and subsequently classified using fully connected layers and a SoftMax classifier. Experimental results demonstrated that integrating climate intelligence with image-based deep learning significantly improved disease classification performance. The proposed multimodal framework achieved an overall classification accuracy of 99%, outperforming the conventional image-only CNN models. The inclusion of climate features improved precision, recall and overall robustness by enabling the model to learn correlations between environmental conditions and disease patterns. The framework also demonstrated strong capability in distinguishing visually similar diseases under varying field conditions. Unlike the conventional image-centric approaches, the proposed framework introduced an environmentally contextualized disease recognition model, integrating CNN derived visual features with regional climate information, capable of supporting early warning systems and precision agriculture applications.