High-resolution crop yield and water productivity dataset generated using random forest and remote sensing

Abstract

Accurate and high-resolution crop yield and crop water productivity (CWP) datasets are required to understand and predict spatiotemporal variation in agricultural production capacity; however, datasets for maize and wheat, two key staple dryland crops in China, are currently lacking. In this study, we generated and evaluated a long-term data series, at 1-km resolution of crop yield and CWP for maize and wheat across China, based on the multiple remotely sensed indicators and random forest algorithm. Results showed that MOD16 products are an accurate alternative to eddy covariance flux tower data to describe crop evapotranspiration (maize and wheat RMSE: 4.42 and 3.81 mm/8d, respectively) and the proposed yield estimation model showed accuracy at local (maize and wheat rRMSE: 26.81 and 21.80%, respectively) and regional (maize and wheat rRMSE: 15.36 and 17.17%, respectively) scales. Our analyses, which showed spatiotemporal patterns of maize and wheat yields and CWP across China, can be used to optimize agricultural production strategies in the context of maintaining food security.

ChinaWheatYield30m: a 30 m annual winter wheat yield dataset from 2016 to 2021 in China

“…Random forest (RF) is a model with predictive performance commonly used in the current yield estimation literature (Li et al, 2020;Cheng et al, 2022;Luo et al, 2022). RF regression is a classic ensemble machine learning model that establishes multiple unrelated decision trees by randomly extracting samples and features and obtains the prediction results in parallel.…”

“…Generally, a semi-mechanistic model has great potential in yield estimation, but its application is often limited to a relatively small area, e.g., farm, county or city scale, rather than a larger scale. National crop yield datasets, which are of great significance for large-scale agricultural resource allocation, agricultural system model construction and climate change impact assessment, are produced at coarse spatial resolutions (Table 1), e.g., 0.5 • , 10 km, 4 km or 1 km resolution (Monfreda et al, 2008;You et al, 2014;Iizumi and Sakai, 2020;Grogan et al, 2022;Luo et al, 2022;Cheng et al, 2022), and are mostly downscaled based on the statistical yield datasets and other datasets (Monfreda et al, 2008;You et al, 2014;Iizumi and Sakai, 2020;Grogan et al, 2022). This method of yield downscaling may lead to inaccurate yield estimates and incorrect assessments of the impact of climate change.…”

“…In addition, yield predictions cannot rely on statistical data alone. Luo et al (2022) and Cheng et al (2022) developed yield datasets combining coarse-resolution real-time remote sensing data with agricultural statistics, but because 1 km × 1 km plots or 4 km × 4 km farmlands are rare in China, their field application is limited. Although these datasets are useful for analyzing larger-scale temporal and spatial changes in yield, they cannot deal with small-scale spatial heterogeneity, which happens to be the most significant characteristic of the Chinese farmers' economy.…”

Simulating the effects of optimizing sowing date and variety shift on maize production at finer scale in northeast China under future climate

“…For instance, Zhang et al 37 combined machine learning with a crop model to simulate maize yield in China and achieved an R 2 of 0.56 when comparing the simulations with records from agro-meteorological sites. Similarly, Cheng et al 40 utilized random forest to simulate wheat and maize yield, obtaining an R 2 of 0.51 for wheat and an R 2 of 0.65 for maize when comparing the simulations with in situ observations. 2.…”

Anthropogenic influence on extreme temperature and precipitation in Central Asia

“…Climate impact assessments at regional and national scales require high-resolution climate data. GCM outputs are usually downscaled at higher resolutions for climate impact modelling like hydrological simulations 27 , adaptation strategies 28 , and agriculture studies 29 . Additionally, impact models are usually tuned by local observations.…”