Crop improvement efforts are critical to sustain food production to feed global population and combat adverse effects of climate change. In a typical crop improvement/breeding program, germplasms are evaluated at multiple locations for multiple years to capture crop responses across multiple G x E scenarios prior to a release of a variety for commercial production. Recent advances in phenomics - high-throughput multi-dimensional phenotyping through sensing and automation - have the potential to facilitate objective and quantitative assessment of crop performance, thereby allowing informed and confident selection of high performing varieties in breeding programs through phenomics-assisted selection. Similarly, modeling is a means to understand performance across a variety of environments - beyond what is feasible via field experiments - in a cost- and time-efficient manner, thus complementing field experiments. Integrating phenomics and modeling into the breeding cycle has the potential to increase the genetic gain via data-informed improved selection accuracy towards enhanced yield potential. Improved identification of superior genotypes across a wide range of environments will also enhance the selection process. Therefore, the major goal in this project is to develop and demonstrate a decision support system involving the integration of phenomics and modeling approaches for an informed climate-adapted crop germplasm selection in breeding programs.