Forest cover plays an important role in sustaining ecological security to realize Sustainable Development Goals (SDGs). The research target area is composed of the African region which is experiencing unprecedented deforestation based on the data collection from 54 countries and regions between 2000 and 2020. Spatial autocorrelation analysis, global principal component analysis, and geographic detector model have been used as the core research tool. The temporal and spatial patterns of forest cover change in Africa and the driving effects of population growth, economic and trade, social development, arable land expansion, and other factors on forest cover change in different periods have been demonstrated. The findings are as follows: 1) extremely unequal distribution of Africa forest has caused forest area reduction in 20 years. The reduction quantity of forest has been illustrated from strong to weak: Central Africa (strongest), East Africa (higher strong), West Africa (medium), South Africa (higher weak), and North Africa (weakest). However, the forest reduction area in West Africa with the original ratio is the most significant. More than 80% of the forest area reduction in Africa has occurred in 14 countries, just five national forest areas to achieve the net growth, but the increase amount was only 1% of loss amount. 2) The spatial pattern of forest cover change in Africa contracted and clustered gradually, especially after 2012. Algeria was the hotspot cluster of Morocco and Tunisia, forming the increase area of forest cover in North Africa. Zambia, the coldest point, gathers Angola significantly, while the Democratic Republic of the Congo and Tanzania form a significantly reduced forest cover area. 3) Total population, land area, cultivated land, urban population, consumer price index, and birth rate are the main factors influencing the temporal evolution of forest cover change in Africa. It can be divided into four stages to interpret the different explanations and significance of each factor for forest cover change in the study area.

In the context of carbon neutrality, forest cover change detection has become a key topic of global environmental monitoring. As a large-scale monitoring technique, remote sensing has received obvious attention in various land cover observation applications. With the rapid development of deep learning, remote sensing change detection combined with deep neural network has achieved high accuracy. In this paper, the deep neural network is used to study forest cover change with Landsat images. The main research ideas are as follows. (1) A Siamese detail difference neural network is proposed, which uses a combination of concatenate weight sharing mode and subtract weight sharing mode to improve the accuracy of forest cover change detection. (2) The self-inverse network is introduced to detect the change of forest increase by using the sample data set of forest decrease, which realizes the transfer learning of the sample data set and improves the utilization rate of the sample data set. The experimental results on Landsat 8 images show that the proposed method outperforms several Siamese neural network methods in forest cover change extraction.