Various forms of machine learning (ML) methods have historically played a valuable role in environmental remote sensing research. With an increasing amount of “big data” from earth observation and rapid advances in ML, increasing opportunities for novel methods have emerged to aid in earth environmental monitoring. Over the last decade, a typical and state-of-the-art ML framework named deep learning (DL), which is developed from the traditional neural network (NN), has outperformed traditional models with considerable improvement in performance. Substantial progress in developing a DL methodology for a variety of earth science applications has been observed. Therefore, this review will concentrate on the use of the traditional NN and DL methods to advance the environmental remote sensing process. First, the potential of DL in environmental remote sensing, including land cover mapping, environmental parameter retrieval, data fusion and downscaling, and information reconstruction and prediction, will be analyzed. A typical network structure will then be introduced. Afterward, the applications of DL environmental monitoring in the atmosphere, vegetation, hydrology, air and land surface temperature, evapotranspiration, solar radiation, and ocean color are specifically reviewed. Finally, challenges and future perspectives will be comprehensively analyzed and discussed.

Introduction

The earth’s environmental deterioration, which is caused by human behavior and is continuously aggravating, has become the primary problem hindering further developments of global changes. The lack of resources and environmental deterioration are no longer exclusive phenomena in specific regions. In the last 50 years, space information technology, especially satellite remote sensing technology, has provided advanced detection and research means for the investigation of the earth’s resources, the monitoring of local and regional environmental changes, and even the study of global changes, with the advantages of being macro, comprehensive, fast, dynamic, and accurate (Overpeck et al., 2011; Yang et al., 2013). Remote sensing data are mainly used for environmental parameter monitoring based on physical models (Liang, 2005). Although physical models can effectively express the formation process from environmental parameters to remote sensing observations, these models are largely dependent on the prior knowledge of the model parameters. Such knowledge often has large uncertainty due to the high complexity of the physical process and varies in different periods and regions, which tends to result in the limited accuracy of environmental remote sensing.