LSTM-attention-guided graph neural networks for integrated genotype–Environment modeling in maize yield prediction
Open Access
- 20 May 2026
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (5) , e1013729
Abstract
This paper presents a deep-learning framework that combines an LSTM, a graph neural network (GNN), and transformer-style attention to model genotype–environment (G×E) effects for maize yield prediction. Weather data for a growing season is summarized using LSTM and encoded into a 21-dimensional embedding that is used as the environment node feature; 437,214 SNPs are summarized into 548 principal components that instantiate genotype nodes. Multi-head attention dynamically weights the edges during message passing. Three architectures are compared: A (fully bipartite graph), B (A with intra-set top- k similarity within genotype and within environment), and C (B with a single learnable supernode readout that attends over all nodes after message passing). The joint representations feed a compact MLP for yield prediction. Using a forward-time split (2014–2021 train; 2022 test with unseen genotypes and unseen environments), performance improves monotonically from A to C: A (RMSE 2.7749, PCC 0.4115, R 2 0.1693), B (2.3683, 0.6622, 0.4385), C (2.2120, 0.6945, 0.4823). Compared to A, C has a reduction in RMSE by 0.5629 (∼20.3%) and an increase in PCC by 0.283 (∼68.8%), indicating that global, content-adaptive aggregation promotes local G×E propagation. Performance of proposed approach remains consistent regardless of the number of genotypes per environment and has strong performance under variable or unbalanced genotype sampling expression across environments. The proposed approach is compared with methods from the Global G×E Prediction Competition and show that two of three architectures improve predictive performance, with the best architecture achieving a lower RMSE (2.2120) and a higher Pearson correlation (0.6945) than the competition-winning model.Keywords
All Related Versions
Funding Information
- Natural Sciences and Engineering Research Council Discovery
This publication has 34 references indexed in Scilit:
- Enhancing prediction accuracy of key biomass partitioning traits in wheat using multi‐kernel genomic prediction models integrating secondary traits and environmental covariatesThe Plant Genome, 2025
- Prediction of sugar beet yield and quality parameters using Stacked-LSTM model with pre-harvest UAV time series data and meteorological factorsArtificial Intelligence in Agriculture, 2025
- Large-scale crop dataset and deep learning-based multi-modal fusion framework for more accurate G
×
E genomic predictionComputers and Electronics in Agriculture, 2024
- Using machine learning to combine genetic and environmental data for maize grain yield predictions across multi-environment trialsTheoretical and Applied Genetics, 2024
- GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yieldArtificial Intelligence in Agriculture, 2023
- Multivariate Statistical Machine Learning Methods for Genomic Prediction2022
- Multimodal performers for genomic selection and crop yield predictionSmart Agricultural Technology, 2021
- A reaction norm model for genomic selection using high-dimensional genomic and environmental dataTheoretical and Applied Genetics, 2013
- Supervised Sequence Labelling2012
- The importance of the anthesis-silking interval in breeding for drought tolerance in tropical maizeField Crops Research, 1996