da Matta, D. H. | bioRxiv Science

bioRxiv2022

Data-driven machine learning for pattern recognition supports environmental quality prediction for irrigated rice in Brazil

The sustainability of irrigated rice (Oryza sativa L.) production systems in Brazilian tropical region highly depends on the success of developing stable cultivars. To achieve this goal, many steps in product development must address the environmental variability and genotype by environment interactions (GE), which makes difficult the design and development of local-specific adapted cultivars. Thus, the adoption of new strategies for characterizing environmental-phenotype relations are the key for optimizing this process. In addition, it could also benefit post-breeding stages of seed production. To overcome this situation, we implemented a data-driven approach to link environmental characterization to yield clustering using historical data (1982-2017, 31 locations, 471 genotypes), 42 envirotyping covariables and machine learning (ML), combining two unsupervised (K-means and decision tree models, DTC) algorithms. Additionally, linear mixed models (LMM) were applied to explore the relations between the outcomes of our approach and GE analysis for irrigated rice yield in Brazilian tropical region. Four environments were identified: Very Low Yield (1.7 Mg.ha-1), Low Yield (5.1 Mg.ha-1), High Yield (7.2 Mg.ha-1), and Very High Yield (9.0 Mg.ha-1), considering all genotypes and regions. Our approach allows the prediction of environments (yield clusters) for a diverse set of growing conditions and revealed geographic and climatic causes of environmental quality, which differ according to each region and genotype group. From the LMM analysis, we found that the current relation between genetics (G), environmental variation (E), and GE for rainfed rice in Brazil is 1:6:2, but when we introduced our data-driven clusters (ME), the ratio decreased to 1:5:1. Consequently, the selection reliability for local adaptability across an extensive region increases. Our approach helps to identify mega-environments in Brazil that could be used as a target population of environments (TPE) of breeding programs. Additionally, it helps to identify more productive and stable seed production fields. HighlightsO_LIA nationwide environmental characterization and its relation to the genotype by environment interaction (GE) for grain yield of rainfed rice growing regions in Brazil. C_LIO_LIA data-driven approach capable to identifying clusters of yield levels and a machine learning approach to relate those clusters with environmental typologies. C_LIO_LIUnrevealed geographic and climatic causes of environmental quality for a group of genotypes or cultivar-specific predictions. C_LIO_LIThe strategy benefits diverse stages of breeding (multiple environmental trial analysis) and post-breeding (selection of fields for seed production) as an alternative approach to reduce costs and support decisions on cultivar planting locations. C_LI

genetics↗

bioRxiv2022

Enviromic prediction is useful to define the limits of climate adaptation: A case study of common beans in Brazil

Future environmental shifts foster plant research aiming to develop climate-smart cultivars but the past and current impacts on the environment are also a key to unraveling a major part of the phenotypic adaptation of crops. These studies may determine the most relevant environmental components of yield stability and adaptability within a breeding framework. Here, as a proof-concept study, we quantified the impacts of climate drivers in adapting common bean across Brazilian regions and seasons. We developed an enviromic prediction approach based on Generalized Additive Models (GAM), large-scale environmental covariate data (EC), and grain yield (GY) of 18 years of a common bean breeding program. Then, we predicted the optimum limits for ECs for each production scenario. We verified the ability of GAM-based models to explain the climate driver GY variation and performed accurate predictions for diverse production scenarios (four regions, three seasons, and two grain types). Our results indicates that air temperature (maximum and minimum), accumulated solar radiation, and rainfalls are mostly associated as the main drivers of GY variation in most regions. We also observed a huge variability of the climate drivers impact for the same germplasm cultivated across different seasons for each region. Furthermore, this climate influence in common beans adaptation is more evident during the vegetative for some seasons, while more impressive for reproductive stages for other seasons. Consequently, it demands higher efforts from breeding programs in developing region- or season-specific ideotype cultivars. Enviromics prediction with GAM was useful to identify the effect of climate on critical crop stages, which indirectly might help breeders in developing climate-smart varieties. We envisage its use with research field trial data (e.g., advanced yield testing) and historical farm field yield aimed at understanding breeding gaps in developing adapted cultivars for growing scenarios. HighlightsO_LIWe developed an enviromic prediction approach based on Generalized Additive Models (GAM) for a large-scale environmental covariate data and grain yield C_LIO_LIWe verified the ability of GAM-based models to explain the climate driver grain yield variation and performed accurate predictions for diverse production scenarios (four regions, three seasons, and two grain types) C_LIO_LIClimatic limitations for cropping commun beans were identified across seasons and regions. C_LIO_LI"Optimum" values for climate variables in different common bean regions productions were obtained . C_LI

genetics↗