Application of a Fusion Attention Mechanism-Based Model Combining Bidirectional Gated Recurrent Units and Recurrent Neural Networks in Soil Nutrient Content Estimation
Open Access
Abstract
Accurately estimating soil nutrient content, including soil organic matter (OM), nitrogen (N), phosphorus (P), and potassium (K) levels, is crucial for optimizing agricultural practices and ensuring sustainable crop production. This paper proposes a model based on a fusion attention mechanism that combines bidirectional gated recurrent units (BiGRU) and recurrent neural networks (RNN) to estimate soil nutrient content. The proposed model integrates the fused attention mechanism with BiGRU and RNN to enhance the accuracy and effectiveness of soil nutrient prediction. The fused attention mechanism captures key features in the input data, while the BiGRU architecture captures both forward and backward contextual information, enabling the model to capture long-term dependencies in the data. The results demonstrate that the proposed Att-BiGRU-RNN model outperforms other constructed models, exhibiting a higher prediction accuracy and robustness. The model shows good estimation capabilities for soil OM, N, P, and K with estimation accuracies (R2) of 0.959, 0.907, 0.921, and 0.914, respectively. The application of this model in soil nutrient estimation has the potential to optimize fertilizer management, enhance soil fertility, and ultimately improve crop yield. Further research can explore the applicability of this model in precision agriculture and sustainable soil management practices, benefiting the agricultural sector and contributing to food security and environmental sustainability.Keywords
Funding Information
- Major Science and Technology Special Projects in Xinjiang Uygur Autonomous Region (2022A0201-4, 51365048, YTHSD2022-03)
- National Natural Science Foundation of China (2022A0201-4, 51365048, YTHSD2022-03)
- Xinjiang Agricultural Machinery R&D, Manufacturing, Promotion, and Application Integration Project (2022A0201-4, 51365048, YTHSD2022-03)
This publication has 52 references indexed in Scilit:
- Fertilizer placement to improve crop nutrient acquisition and yield: A review and meta-analysisField Crops Research, 2016
- Analysis of field-scale spatial correlations and variations of soil nutrients using geostatisticsEnvironmental Monitoring and Assessment, 2016
- Modeling some real phenomena by fractional differential equationsMathematical Methods in the Applied Sciences, 2015
- Formation of soil organic matter via biochemical and physical pathways of litter mass lossNature Geoscience, 2015
- Evaluation Models for Soil Nutrient Based on Support Vector Machine and Artificial Neural NetworksThe Scientific World Journal, 2014
- Nutrient availability limits carbon sequestration in arable soilsSoil Biology and Biochemistry, 2014
- HONO Emissions from Soil Bacteria as a Major Source of Atmospheric Reactive NitrogenScience, 2013
- A portable soil nitrogen detector based on NIRSPrecision Agriculture, 2013
- Soil microbial biomass and the fate of phosphorus during long-term ecosystem developmentPlant and Soil, 2012
- Assessing soil fertility of a laterite soil in relation to yield of arecanut (Areca catechu L.) in humid tropics of IndiaGeoderma, 2012