Populus Euphratica has always been one of the most important vegetation types in desert regions, playing a crucial role in maintaining the ecological balance of the desert ecosystem. With the development of remote sensing technology, large-scale monitoring of Populus Euphratica forests through remote sensing has become feasible. However, the extraction of Populus Euphratica forests faces two key challenges: Spectral Confusion and Complex Spatial Distribution. Although existing extraction methods consider temporal features, they have not fully utilized the spatiotemporal information. To address this, we propose a spatiotemporal-based multi-source remote sensing method for Populus Euphratica forest extraction, named STP-Net (Spatiotemporal Populus Euphratica Extraction Network). This method fully integrates the spatiotemporal information of multi-source remote sensing satellite images to accurately extract Populus Euphratica forests. Furthermore, to validate and assess the performance of the algorithm, we created a dataset for the Populus Euphratica forest extraction task based on multi-source spatiotemporal satellite imagery. The experimental results demonstrate that our algorithm outperforms current state-of-the-art methods in the task of extracting Populus Euphratica forests, and it also offers a fast mapping speed, making it suitable for large-scale mapping of Populus Euphratica forests.