High-resolution image and machine learning-based high-altitude region crop classification and identification method

Abstract

The invention discloses a high-resolution image and machine learning-based high-altitude region crop classification and identification method, which comprises the following steps of: screening out an optimal feature combination through a recursive feature elimination strategy based on a random forest by using a domestic GF6-PMS satellite image and combining features such as spectrum, texture, vegetation index and topographic factor; and calculating a Gini index to obtain an importance score of each input feature, and further utilizing a two-layer stack-driven integrated classification model (including three single classifier models of Random Forest, XGBoost and AdaBoost) to classify and identify the crops in the high-altitude region. The Stacking model constructed on the basis of the optimal feature combination (Green, Red, NIR, TVI, GNDVI, BlueMean, GreenMean, RedMean, NIRMean, DEM) can improve the classification and recognition precision of crops in high-altitude areas to a large extent, especially the classification and recognition precision of bulk crops with large planting areas, and provides a scientific reference basis for crop remote sensing recognition of domestic high-resolution satellite images in high-altitude areas.

Description

technical field [0001] The invention relates to the field of dynamic monitoring of cultivated land changes in high-altitude areas based on domestic high-resolution satellite images, in particular to a method for classifying and identifying crops in high-altitude areas based on high-resolution images and machine learning. Background technique [0002] Continued growth in the global population is increasing the risk of food shortages, and the world is facing ongoing food security challenges. With the continuous reduction of cultivated land area brought about by the increase of my country's population, my country's agricultural production has been accelerated to the direction of intensification and precision. With this shift in agricultural production patterns, there is a need to monitor agricultural systems more effectively, providing detailed spatial information about crop types in a timely and accurate manner. Obtaining key information such as crop spatial distribution, gro...

AI Technical Summary

Problems solved by technology

[0007] Existing research on crop identification is mostly concentrated in plain areas, and research on crop classification and identification in high-altitude areas is rarely involved; and the advantages of domestic high-resolution image data in crop classification and identification in high-altitude areas have not yet been clarified. The classification effect of the Stacking model in high-altitude areas still needs further research

Images