agriculture papers | Gist.Science

Hyperspectral–Region Aggregation Network for Maize Leaf Nitrogen Content Estimation via Spectral–Regional Joint Modeling

This study proposes the Hyperspectral–Region Aggregation Network (HSRAN), a deep learning framework that integrates spectral adaptive recalibration and context-aware gated aggregation to effectively address spectral redundancy and regional heterogeneity, thereby achieving superior accuracy in estimating maize leaf nitrogen content across various growth stages compared to traditional and existing deep learning models.

Fuheng Qu, Mingyang Zhu, Xiaofeng Li, Li Zhu, Chunran Wu, Peng Gao2026-09-08

📄 agriculture

Assessing served portions plate waste and student acceptability in the Indonesian Free Nutritious Meal Program at a vocational high school

This study evaluates the Indonesian Free Nutritious Meal Program at a vocational high school, revealing that while animal-source dishes and staples are well-accepted, vegetables and plant-based sides face significant challenges due to low acceptability, high plate waste, and portion inconsistencies, necessitating targeted menu reformulation and standardization.

Ai Nurhayati, M. Muktiarni, Rita Patriasih, Ai Mahmudatusaadah, Tati Setiawati2026-09-08

📄 agriculture

Scaling native hedgerows in Mediterranean greenhouse horticulture requires alignment of farm design, learning, and governance

This study reveals that scaling native hedgerows in Mediterranean greenhouse horticulture depends not merely on awareness of pest control benefits, but on a coupled-innovation configuration that aligns farm-compatible ecological design, situated learning through trusted networks, and institutional governance to overcome spatial, legal, and coordination barriers.

Irene Pérez-Ramírez, Enrica Garau, Nora Schütze, Juan Miguel Requena-Mullor, Álvaro Peláez-Pérez, Gabriela De Abreu, Ant (…)2026-09-08

📄 agriculture

Application of Machine Learning Random Forest Algorithm in Digital Soil Mapping of Key Soil Properties for Sustainable Tea Productivity

This study demonstrates that a Random Forest machine learning algorithm integrated with SCORPAN-based environmental covariates can effectively predict key soil properties in Tanzania's Ganyange Ward, generating spatial maps that reveal moderately favorable, acidic conditions for sustainable tea productivity and serving as a valuable decision-support tool for land-use planning.

Finias F. Mwesige, Boniface H. J. Massawe, Hilda G. Sanga, Braison E. Mjanja, Erasto Focus2026-09-08

📄 agriculture

A Multimodal Deep Learning Approach to Bacterial Wilt Detection in Ginger Plants

This study proposes a multimodal deep learning approach for detecting bacterial wilt in ginger plants, demonstrating that a hybrid CNN + Graph Neural Network (GNN) model outperforms CNN + RNN and CNN + Vision Transformer combinations by achieving a superior accuracy of 96.85%.

Gagana S, Ravi Kumar V, Vinay B K, Kavitha Sooda2026-09-08

📄 agriculture

Physics-Informed Neural Network for Daily Canopy Size Forecasting in Strawberry Production Using Fused Weather and Image Embeddings

This study developed a hybrid Physics-Informed Neural Network (PINN) that fuses weather data and image-derived green pixel counts to accurately forecast daily strawberry canopy volume, demonstrating superior performance over baseline models for two commercial cultivars under real-world field conditions.

Rohan Bagulwar, Won Suk Lee, Shinsuke Agehara, Hongyoung Jeon, Heping Zhu2026-09-08

📄 agriculture

The Influence of the Slenderness Coefficient on Urban Tree Stability: An Acoustic Tomography Assessment Across Seven Taxa

This ten-year study of 2,053 urban trees in Slovakia using 3D acoustic tomography demonstrates that the traditional slenderness coefficient (H/D ratio) is an inadequate universal predictor of tree stability, necessitating a shift toward species-specific risk assessments that integrate internal decay analysis and morphometric data.

Radovan Ostrovský, Marek Kobza, Marcel Raček2026-09-08

📄 agriculture

Mining a tomato core collection for resistance to TSWV, ToMV and Fusarium oxysporum f. sp. lycopersici

This study screened a tomato core collection for resistance to TSWV, ToMV, and FOL, identifying valuable multi-pathogen resistant accessions and novel genetic loci through phenotypic and molecular analyses to support the development of durable, resilient tomato varieties.

Leandro Pereira-Dias, Poleth Bermeo, Maria R. Figàs, Gabriele Campanelli, Pasquale Tripodi, Isabel López-Cortés, Jaime P (…)2026-09-08

📄 agriculture

Rice husk fly ash as a soil amendment for dry season rice (Oryza sativa L.) grown in the peat soil of Bangladesh

This study demonstrates that applying rice husk fly ash to peat soil in Bangladesh significantly improves soil fertility by correcting pH and salinity while enhancing nutrient availability, ultimately leading to increased growth and grain yield in dry-season rice varieties.

Md. Romel Biswash, Khondoker Khalid Ahmed, Md Hymun Kabir Baktier, Umme Aminun Naher, Amina Khatun, Md Habibur Rahman Mu (…)2026-09-08

📄 agriculture

Edge-Enabled Deep Learning and Multi-Model Hybrid Intelligent Architectures Integrating Sentinel-3 and MODIS Data for Real-Time Monitoring of Crop Stress and Nonlinear Pest Complexes Forecasting Under Climate Shifts

This study presents an edge-enabled hybrid deep learning architecture integrating Sentinel-3 and MODIS data to achieve highly accurate, real-time forecasting of pigeonpea pest dynamics and crop stress under climate shifts, outperforming state-of-the-art models while supporting sustainable smallholder agriculture.

MRK Pathan, Mst. Rasheda Chowdhury2026-09-08