Maize yield estimation in Northeast China’s black soil region using a deep learning model with attention mechanism and remote sensing DOI Creative Commons
Xingke Li,

Yunfeng Lv,

Bingxue Zhu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 15, 2025

Abstract Accurate prediction of maize yields is crucial for effective crop management. In this paper, we propose a novel deep learning framework (CNNAtBiGRU) estimating yield, which applied to typical black soil areas in Northeast China. This integrates one-dimensional convolutional neural network (1D-CNN), bidirectional gated recurrent units (BiGRU), and an attention mechanism effectively characterize weight key segments input data. the predictions most recent year, model demonstrated high accuracy (R² = 0.896, RMSE 908.33 kg/ha) exhibited strong robustness both earlier years during extreme climatic events. Unlike traditional yield estimation methods that primarily rely on remote sensing vegetation indices, phenological data, meteorological characteristics, study innovatively incorporates anthropogenic factors, such as Degree Cultivation Mechanization (DCM), reflecting rapid advancement agricultural modernization. The relative importance analysis variables revealed Enhanced Vegetation Index (EVI), Sun-Induced Chlorophyll Fluorescence (SIF), DCM were influential factors prediction. Furthermore, our enables 1–2 months advance by leveraging historical patterns environmental variables, providing valuable lead time decision-making. predictive capability does not forecasting future weather conditions but rather captures yield-relevant signals embedded early-season

Language: Английский

Combining Machine Learning Algorithms with Earth Observations for Crop Monitoring and Management DOI Creative Commons
Magdalena Piekutowska, Gniewko Niedbała, Sebastian Kujawa

et al.

Agriculture, Journal Year: 2025, Volume and Issue: 15(5), P. 494 - 494

Published: Feb. 25, 2025

Combining machine learning algorithms with Earth observations has great potential in the context of crop monitoring and management, which is essential face global challenges related to food security climate change [...]

Language: Английский

Citations

0
Leveraging Artificial Intelligence for Enhancing Wheat Yield Resilience Amidst Climate Change in Sub-Saharan Africa DOI
Petros Chavula, Fredrick Kayusi,

Linety Juma

et al.

LatIA, Journal Year: 2025, Volume and Issue: 3, P. 88 - 88

Published: Feb. 19, 2025

The introduction of a deep learning-based method for non-destructive leaf area index (LAI) assessment has enhanced rapid estimation wheat and similar crops, aiding crop growth monitoring, water, nutrient management. Convolutional Neural Network (CNN)-based algorithms enable accurate, quantification seedling areas assess LAI across diverse genotypes environments, demonstrating adaptability. Transfer learning, known efficiency in plant phenotyping, was tested as resource-saving approach training the model. These advancements support breeding, facilitate genotype selection varied accelerate genetic gains, enhance genomic LAI. By capturing this can improve resilience to climate change. Additionally, advances machine learning data science better prediction distribution mapping global rust pathogens, major agricultural challenge. Accurate risk identification allows timely effective control measures. Moreover, lodging models using CNNs lodging-prone varieties, influencing decisions yield stability. artificial intelligence-driven techniques contribute sustainable enhancement, especially context change increasing food demand.

Language: Английский

Citations

0
Enhancing Agricultural Cybersecurity DOI
Hewa Majeed Zangana, Senny Luckyardi,

Firas Mahmood Mustafa

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 307 - 338

Published: April 8, 2025

The rapid digital transformation of agriculture through smart farming technologies has introduced new cybersecurity challenges that threaten the integrity, confidentiality, and availability critical agricultural data systems. As precision agriculture, Internet Things (IoT)-enabled sensors, automated decision-making become integral to modern farming, risks associated with cyber threats—such as breaches, ransomware attacks, supply chain vulnerabilities—continue escalate. Unlike traditional security measures, AI-driven solutions, including deep learning Large Language Models (LLMs), offer real-time threat detection, adaptive defense mechanisms, enhanced risk assessment capabilities. This chapter explores application these in securing networks, from intrusion detection incident response. It also presents case studies solutions implemented environments.

Language: Английский

Citations

0
Maize yield estimation in Northeast China’s black soil region using a deep learning model with attention mechanism and remote sensing DOI Creative Commons
Xingke Li,

Yunfeng Lv,

Bingxue Zhu

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 15, 2025

Abstract Accurate prediction of maize yields is crucial for effective crop management. In this paper, we propose a novel deep learning framework (CNNAtBiGRU) estimating yield, which applied to typical black soil areas in Northeast China. This integrates one-dimensional convolutional neural network (1D-CNN), bidirectional gated recurrent units (BiGRU), and an attention mechanism effectively characterize weight key segments input data. the predictions most recent year, model demonstrated high accuracy (R² = 0.896, RMSE 908.33 kg/ha) exhibited strong robustness both earlier years during extreme climatic events. Unlike traditional yield estimation methods that primarily rely on remote sensing vegetation indices, phenological data, meteorological characteristics, study innovatively incorporates anthropogenic factors, such as Degree Cultivation Mechanization (DCM), reflecting rapid advancement agricultural modernization. The relative importance analysis variables revealed Enhanced Vegetation Index (EVI), Sun-Induced Chlorophyll Fluorescence (SIF), DCM were influential factors prediction. Furthermore, our enables 1–2 months advance by leveraging historical patterns environmental variables, providing valuable lead time decision-making. predictive capability does not forecasting future weather conditions but rather captures yield-relevant signals embedded early-season

Language: Английский

Citations

0