The Innovation Team of the Agricultural Allocation and Regional Development of the Institute of Agricultural Resources and Regional Planning (IARRP) of the Chinese Academy of Agricultural Sciences (CAAS) has made important progress in the estimation of potato aboveground biomass and the uncertainty of crop climate suitability. The study was conducted in cooperation with local universities.

The research results entitled "Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on UAV multispectral imagery" and "Identifying sources of uncertainty in wheat production projections with consideration of crop climatic suitability under future climate" were published in journals such as Frontiers in Plant Science and Agricultural and Forest Meteorology.

According to Professor He Yingbin, a research fellow at the IARRP of the CAAS, aboveground biomass (AGB) is an important indicator for evaluating potato growth and development, guiding field agricultural production management, and characterizing yield. This paper predicts the potato AGB using partial least squares regression (PLSR) and random forest regression (RFR) from parameters without variable selection and using different methods for variable selection. It also explains the effects of different dimensional variables in potato AGB estimation and the differences between different methods of feature selection. The models and technologies proposed can achieve accurate estimation of the high and low values of potato AGB, and provide theoretical and technical support for rapid extraction of crop remote sensing phenotype information and high-throughput screening of plant phenotypes.

In addition, a combination of crop growth models (CMs), global climate models (GCMs), and species distribution models (SDMs) are commonly used to assess the impact of climate change on crop yields. However, there are few studies on the sources of uncertainty in wheat yield prediction considering crop climatic suitability under future climatic conditions. Based on the combination of CMs, SDMs, and GCMs, the paper analyzes the impact of climate change on the yield of winter wheat in the Loess Plateau and focuses on the uncertainty of the uncertain sources of different combination methods of CMs, SDMs, and GCMs. The study found that the uncertainty of CMs is low, and the research method is helpful in reasonably integrating CMs, SDMs, and GCMs to carry out simulation and prediction of wheat yield under future climate change scenarios.

The research work was jointly funded by the Science and Technology Innovation Project of the Chinese Academy of Agricultural Sciences and the National Natural Science Foundation of China.

Paper links: (1) https://doi.org/10.3389/fpls.2022.948249

                  (2)https://doi.org/10.1016/j.agrformet.2022.108933