Grain yield (GY) is a primary trait for phenotype selection in crop breeding. Rapid and cost-effective phenotyping of GY before harvest from remote sensing platforms can be integrated with practical breeding activities. In this study, a natural population containing 166 wheat cultivars and elite lines were used for time-series prediction of GY using UAV based multispectral remote sensing. UAV based images were collected at the flowering, early grain filling (EGF), mid grain filling (MGF) and late grain filling (LGF) stages under four environments. GY was predicted by using 20 vegetation indices as inputs of deep neural network (DNN). Whereas genome-wide association study (GWAS) was performed using 373,106 markers from 660K and 90K SNP arrays in 166 wheat genotypes. Prediction accuracy for GY using full band reflectance characterized by R2 values were 0.78, 0.79, 0.76 and 0.65 at flowering, EGF, MGF and LGF, respectively. Among the 20 identified loci for poxy trait used to predict GY, 9 were located at similar positions previously reported as yield-related loci, and 11 are potentially new loci. Linear regression (R2) ranged from 0.79 to 0.84 indicated that distinct cumulative effects of favorable alleles detected by predicted GY was increasing as compare to measured GY. This study highlights the feasibility of combining UAV-based remote sensing with machine learning for wheat breeding decisions and to understand the underlying genetic basis of grain yield.