Optimal deployment of cultivated land quality monitoring points based on
satellite-driven cultivated land quality and improved spatial simulated
annealing
Abstract
The deployment of scientific and reasonable cultivated land quality
(CLQ) monitoring points can provide timely and accurate information on
the current situation and changes in CLQ, which is highly important to
protect national food security. The conventional methods of selecting
CLQ monitoring points are based on the CLQ of land use patches. As there
may be different grades of large patches, being selected as monitoring
points reduces the reliability of monitoring CLQ. Moreover, the
conventional monitoring point deployment method mainly considers only
CLQ and ignores road accessibility and terrain as factors, resulting in
the inaccessibility of some monitoring points. Therefore, to improve the
reliability of CLQ monitoring, this study presented a novel approach for
deploying CLQ monitoring points. First, the pixel-scale CLQ was
estimated using the genetic algorithm-back propagation neural network
(GA-BPNN) model based on the Landstat8 data with 30 m spatial
resolution. Second, the stratified sampling model was used to determine
the optimal sample points. Finally, the improved spatial simulated
annealing algorithm (ISSA), considering both slope and road
accessibility, was applied to optimize the location of monitoring
points. This study was conducted in the Conghua District of Guangzhou,
Guangdong Province, China. The results highlighted that (1) compared to
the accuracy of measured CLQ, the accuracy (R 2
= 0.63, RMSE = 79.32, and
NRMSE = 13.77%) of CLQ estimated using the remote sensing technique was
reliable, and the pixel-scale CLQ data was more reasonable than the
patch-scale CLQ data with different grades. (2) A total of 132
monitoring points were finally identified in the study area based on the
stratified sampling model. (3) When compared with those of the spatial
simulated annealing algorithm (SSA) and the standard grid method, the
approach proposed in this study had a higher total score (F = 94.61).
Moreover, the obtained sample points were mainly located near roads and
flat terrain. This can effectively avoid the inaccessible places. Thus,
the results based on the novel approach proposed in this study provide a
scientific basis and technical support for obtaining the optimal CLQ
monitoring points.