Search

The accurate estimation of cropland net primary productivity (NPP) remains a significant challenge. We hypothesized that incorporating prior information on NPP simulated by process-based models into normalized difference vegetation index (NDVI) data would improve the accuracy of cropland ecosystem NPP estimations. We used NDVI, MNPP (NPP of process-based model), and SNPP (statistic-based NPP) data estimated by nine process-based models and yield statistics to build a learning ensemble of the random forest model (LERFM). We used the new model to re-evaluate the cropland NPP in China from 1982 to 2010. Large spatial discrepancies among MNPPs, which indicate uncertainties in cropland NPP estimation using different methods, were observed when compared to SNPP. The LERFM model showed a slightly underestimation of only −0.37%, while the multi-model average process-based model (MMEM) strongly underestimated −15.46% of the SNPP. LERFM accurately estimated cropland NPP with a high simulation skill score. A consistent increasing trend in the LERFM and MMEM NPP during 1982–2010 and a significant positive correlation (r = 0.795, p < 0.001) between their total NPP indicate that the LERFM model can better describe spatiotemporal dynamic changes in cropland NPP. This study suggests that a learning ensemble method that combines the NDVI and process-based simulation results can effectively improve cropland NPP.

While the eco-environmental effects of rural settlement expansion are of great significance to rural sustainable land use, the relationship between rural settlement expansion and eco-environment under different expansion patterns is still unclear. To fill this gap, the current study used Baota district of the loess hilly and gully region as a case study area. We first investigated the spatiotemporal expansion patterns of rural settlements from 1990 to 2015 and then estimated their impacts on ecosystem services by implementing the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model and the global agro-ecological zones (GAEZ) model. Results showed the following: 1) edge expansion was the primary pattern of rural settlement expansion in Baota district from 1990 to 2015, and the area of edge expansion was 757.40 h m2, accounting for 71.76% of the total expansion area of rural settlements. 2) Rural settlement expansion caused 1744.60 t loss of crop yield, 40,155.78 Mg C loss of carbon storage, and a significant decline in habitat quality of water areas during 1990–2015. 3) According to the unit expansion area, the edge expansion and leapfrog expansion patterns contributed more to ecosystem services loss than the infilling expansion pattern. 4) There were gradient differences in the impacts of three expansion patterns on ecosystem services, and the impacts were gradually weakened by the increased distance. Accordingly, we concluded that the expansion of rural settlements reduced surrounding ecosystem services, especially food production service, and that the edge expansion and leapfrog expansion patterns had higher levels of stress on ecosystem services.