Understanding rice yield gaps with crop modeling and machine learning in a long-term continuous cropping experiment

Le résumé fourni par la source

CONTEXT: Long-term experiments provide opportunities to develop strategies for sustaining rice productivity, improving resource use efficiency, and adapting to abiotic and biotic stresses. Yet yield gap approaches have rarely been applied to such datasets to disentangle the drivers of long-term productivity.OBJECTIVE: We analyzed five decades (1971–2017) of rice yields from the Long-Term Continuous Cropping Experiment (LTCCE) at IRRI to quantify yield gaps, identify causes across dry, early wet, and late wet seasons, and simulate yield under scenarios with constraints removed.METHODS: Potential yields and yield gaps were estimated using the process-based model ORYZA, while machine learning (ML) with Random Forest and SHAP interpretation identified determinants of yield gap variation. Additionally, ML-based yield predictions were compared under scenarios with and without disease pressure and varietal aging to quantify their contribution to yield gaps.RESULTS AND CONCLUSIONS: Actual yields with high fertilizer treatments averaged 64% of potential in the dry season but only 47–52% in the wet seasons. Seasonal constraints varied: tungro disease widened the dry-season gap, extended cropping years reduced the early wet-season gap, and varietal aging increased the late wet-season gap. Accounting for biotic stresses and varietal turnover in ML improved consistency with ORYZA results, especially in wet seasons. The yield gap between ORYZA-simulated potential yields and ML-predicted actual yields narrowed, and yields reached 63–69% of potential when disease and varietal aging were excluded.SIGNIFICANCE: These findings highlight the complementary value of ML and crop simulation models for diagnosing yield gaps and underscore the need for seasonally tailored interventions, particularly more frequent varietal replacement and improved disease management. Leveraging long-term data with modeling provides a robust pathway for understanding and narrowing yield gaps in intensive rice systems.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.