Analysing and simulating spatial patterns of crop yield in Guizhou Province based on artificial neural networks

Abstract

The area of karst terrain in China covers 3.63×106 km2, with more than 40% in the southwestern region over the Guizhou Plateau. Karst comprises exposed carbonate bedrock over approximately 1.30×106 km2 of this area, which suffers from soil degradation and poor crop yield. This paper aims to gain a better understanding of the environmental controls on crop yield in order to enable more sustainable use of natural resources for food production and development. More precisely, four kinds of artificial neural network were used to analyse and simulate the spatial patterns of crop yield for seven crop species grown in Guizhou Province, exploring the relationships with meteorological, soil, irrigation and fertilization factors. The results of spatial classification showed that most regions of high-level crop yield per area and total crop yield are located in the central-north area of Guizhou. Moreover, the three artificial neural networks used to simulate the spatial patterns of crop yield all demonstrated a good correlation coefficient between simulated and true yield. However, the Back Propagation network had the best performance based on both accuracy and runtime. Among the 13 influencing factors investigated, temperature (16.4%), radiation (15.3%), soil moisture (13.5%), fertilization of N (13.5%) and P (12.4%) had the largest contribution to crop yield spatial distribution. These results suggest that neural networks have potential application in identifying environmental controls on crop yield and in modelling spatial patterns of crop yield, which could enable local stakeholders to realize sustainable development and crop production goals.

Determinants of ecosystem processes and services in the karst critical zone in south-west China

“…Regions dominated by magnesium-rich dolomite show the greatest annual variation in GPP, confirming previous work on the poor water storage capacity of the thin soil that has developed on dolomite (Liu et al, 2019). Liang et al (2021) find that the greatest effect on food production is temperature (16.4%), followed by radiation (15.3%), soil moisture (13.5%), fertilization of nitrogen (13.5%) and, finally, phosphorus (12.4%). In total, soil factors, including soil moisture and soil chemical features can contribute up to 40% of the crop yield.…”

Achieving Sustainable Earth Futures in the Anthropocene by Including Local Communities in Critical Zone Science

“…Improve nutrient use efficiency Nutrient cycling Soil N and P explained 13.5% and 12.4% of crop yield variances, respectively, at the Karst CZO (Liang et al, 2020); high risk of environmental pollution prevents increasing crop yield through fertilization (Liang et al, 2021) -Shift from "leaky" to "tight" N-cycling processes (D. Li et al, 2018) -Re-emergence of microbial N-cycling functions in soil after agricultural abandonment (D. Li et al, 2018Li et al, , 2021a 15 Farmers in all CZs identified fertilisers as their greatest cost and one of the top three farming challenges they face (Zheng et al,. 2018, this paper) 1,2 -Reduce N inputs to improve economic livelihoods and well-being -Judicious use of N with crop residue returns increases soil C (X. D. Song et al, 2019a;X.…”

Jennings’Karst(1971, MIT Press) and current critical zone science

“…Furthermore, it has been proved that vegetation restoration activities do not necessarily reduce soil erosion in karst regions because climatic drought events threaten the sustainability of planting and its ability to conserve soil (Feng et al, 2021). Crop yield from an upper slope position would be greatly reduced by soil erosion (Liang et al, 2021), and this type of area may be one where forest planting activities such as those carried out by the Grain for Green project should first be applied. So far, however, the critical zone is only a statement of ‘concept’ rather than a systematic ‘science’, although 20 years have passed since this notion was first put forward in the book Basic Research Opportunities in Earth Science (An et al, 2016; National Research Council, 2001).…”