The estimation of yield parameters based on early data is helpful for agricultural policymakers and food security. Developments in unmanned aerial vehicle (UAV) platforms and sensor technology help to estimate yields efficiency. Previous studies have been based on less cultivars (<10) and ideal experimental environments, it is not available in practical production. Therefore, the objective of this study was to estimate the yield parameters of soybean (Glycine max (L.) Merr.) under lodging conditions using RGB information. In this study, 17 time point data throughout the soybean growing season in Nanchang, Jiangxi Province, China, were collected, and the vegetation index, texture information, canopy cover, and crop height were obtained by UAV-image processing. After that, partial least squares regression (PLSR), logistic regression (Logistic), random forest regression (RFR), support vector machine regression (SVM), and deep learning neural network (DNN) were used to estimate the yield parameters. The results can be summarized as follows: (1) The most suitable time point to estimate the yield was flowering stage (48 days), which was when most of the soybean cultivars flowered. (2) The multiple data fusion improved the accuracy of estimating the yield parameters, and the texture information has a high potential to contribute to the estimation of yields, and (3) The DNN model showed the best accuracy of training (R2=0.66 rRMSE=32.62%) and validation (R2=0.50, rRMSE=43.71%) datasets. In conclusion, these results provide insights into both best estimate period selection and early yield estimation under lodging condition when using remote sensing.

Genome-wide association study (GWAS) identifies trait-associated loci, but due in part to slow decay of linkage disequilibrium (LD), identifying the causal genes can be a bottleneck. Transcriptome-wide association study (TWAS) addresses this by identifying gene expression-phenotype associations or integrating gene expression quantitative trait loci (eQTLs) with GWAS results. Here, we used self-pollinated soybean as a model to evaluate the application of TWAS in the genetic dissection of traits in plant species that exhibit slow LD decay. The first RNA-Seq analysis of a soybean diversity panel was conducted, which identified the genetic regulation of 29,286 genes. Different TWAS solutions were less affected by LD and robust with source of expression that identified known genes related to traits from different development stages and tissues. A novel gene named pod color L2 was identified via TWAS and functionally validated by genome editing. Our introduction of the new exon proportion feature significantly improves the capture of expression variations resulting from structural variations and alternative splicing. As a result, the genes identified by our TWAS approach exhibited a diverse range of causal variations, including SNP, insertion/deletion, gene fusion, copy number variation, and alternative splicing. Using our TWAS approach, we identified genes associated with flowering time, including both previously known candidates and novel genes that had not been linked to this trait before, providing complementary insights with GWAS. In summary, this study supports the application of TWAS for candidate gene identification in species with low rates of LD decay.