Abstract: Farmland is an important guarantee for national security,and its spatial distribution is the main basis for farmland protection,national spatial planning,and other management work,while surface change monitoring is a key support for mastering land use and natural resources.With the development of information technology,deep learning based land cover classification and surface change monitoring have been widely studied.This article explores the intelligent information extraction technology of remote sensing based on deep learning.Using two phases of Jilin-1 satellite remote sensing images covering the experimental area as the data source,a large-scale remote sensing model under the deep learning framework is used to extract agricultural patches from a single phase of remote sensing images and monitor surface changes from two phases of images.The accuracy of the extraction results is evaluated by combining remote sensing images with land survey data.The results indicate that the research method can accurately identify farming patches and changing areas,and the boundary shape matches the image,with good potential for application.

Key words: deep learning, investigation and monitoring, distribution of cultivated land, change detection, natural resources