Agriculture and Forestry University

Explainable lightweight deep learning architectures for crop anomaly detection using enhanced Grad-CAM and transfer learning

This study improves the interpretability of convolutional neural networks (CNNs) for crop anomaly detection while identifying architectures suitable for deployment on resource constraints edge devices. Six CNNs, including the proposed hybrid, were evaluated across 10 crop species...

Development and validation of the “Yucan-1” 5 K liquid chip for genomic studies in the silkworm (Bombyx mori)

The silkworm ( Bombyx mori ) is a lepidopteran model of paramount economic and scientific importance. While genomic resources are available, a high-throughput, cost-effective, and breed-specific genotyping platform for targeted genetic studies in Chinese local breeds, particularl...

Factors affecting the adoption of climate smart aquaculture ( CSAq ) practices among pond fish farmers in Nepal

Abstract Aquaculture is an important sector for Nepal's economy and rural livelihoods, but its long‐term sustainability is increasingly threatened by climate change. Climate Smart Aquaculture (CSAq) has emerged as a promising approach for adaptation, mitigation and productivity e...