The availability of a dense time series of satellite observations at moderate (30 m) spatial resolution is enabling unprecedented opportunities for understanding ecosystems around the world. A time series of data from Landsat was used to generate a series of three maps at decadal time step to show how surface water has changed from 1991 to 2011 in the high northern latitudes of North America. Previous attempts to characterize the change in surface water in this region have been limited in either spatial or temporal resolution, or both. This series of maps was generated for the NASA Arctic and Boreal Vulnerability Experiment (ABoVE), which began in fall 2015. These maps show a “nominal” extent of surface water by using multiple observations to make a single map for each time step. This increases the confidence that any detected changes are related to climate or ecosystem changes not simply caused by short duration weather events such as flood or drought. The methods and comparison to other contemporary maps of the region are presented here. Initial verification results indicate 96% producer accuracy and 54% user accuracy when compared to 2-m resolution WorldView-2 data. All water bodies that were omitted were one Landsat pixel or smaller, hence below detection limits of the instrument.

Circumboreal forests are currently experiencing rapid climate warming which is altering their structure, productivity, and status as a carbon sink. Very high-resolution (VHR; < 2 m) stereo-derived digital surface models are available to monitor these forests, but a similar resolution digital terrain model (DTM) is required to extract information about tree height, which is often used to estimate carbon content. To the best of our knowledge, no openly available VHR DTM currently exists. To address this need, we developed approaches to extract DTMs by filtering VHR stereo point clouds (PCs) in sparse canopies of Alaska. Our evaluation consisted of two stereo processing methods with three PC search radii at six different tree canopy cover (TCC) intervals. We found that VHR DTMs were robust for estimating bare ground at TCC intervals less than 40% with vertical errors < 1.6 m using airborne small footprint light detection and ranging (LiDAR) as reference.

With the significantincrease in the availability of 2-3 daily Harmonized Landsat and Sentinel-2 imagery (HLS), this satellite image time series (SITS) can capture the temporal and spatial features for accurate cropland mapping. This study evaluated the performance of four SITS deep learning (DL) classification approaches, including, convolutional LSTM, convolutional GRU, and 3D UNet, alongside a novel DPC-UNet architecture, for regional cropland mapping inSenegal, using 30 m HLS data. The study focused on the Eastern Casamance (ECAS) and Eastern Transition Zone (ETZ) regions. The study created extensive training data from multidate, 2 m WorldView imagery (WV) covering 15 locations (1500 km$^{2}$) and independently generated ${>}$2000 validation points from the WV images. All the SITS DL models generated cropland maps with high overall accuracy ${>}$ 92% in ECAS and ${>}$ 80% in ETZ. All models displayed relatively low precision of 76 to 80% that was caused by the well-documented overestimation of croplands due to confusion with fallow or abandoned fields and bare sand along drainage lines. The relative performance of the models differed between regions, however, the ConvLSTM marginally had the highest F1 score and overall accuracy in both regions. DPC-UNet displayed the most overestimation in ECAS, but the least in the ETZ. The cropland maps produced by the DL models otherwise displayed strong agreement with the benchmark Global Land Analysis and Discovery (GLAD) cropland map and may also be detecting new expanding fields along the edges of the core cropland clusters. Given their performance and rate of progress, it is likely that SITS DL models will become the standard for operational cropland mapping in the near future, especially with the eminent, dense frequency, 10m HLS data.