Object-Based Detection of Lakes Prone to Seasonal Ice Cover on the Tibetan Plateau

Monitoring the Transformation of Arctic Landscapes: Automated Shoreline Change Detection of Lakes Using Very High Resolution Imagery

Water bodies are a highly abundant feature of Arctic permafrost ecosystems and strongly influence their hydrology, ecology and biogeochemical cycling. While very high resolution satellite images enable detailed mapping of these water bodies, the increasing availability and abundance of this imagery calls for fast, reliable and automatized monitoring. This technical work presents a largely automated and scalable workflow that removes image noise, detects water bodies, removes potential misclassifications from infrastructural features, derives lake shoreline geometries and retrieves their movement rate and direction on the basis of ortho-ready very high resolution satellite imagery from Arctic permafrost lowlands. We applied this workflow to typical Arctic lake areas on the Alaska North Slope and achieved a successful and fast detection of water bodies. We derived representative values for shoreline movement rates ranging from 0.40–0.56 m yr−1 for lake sizes of 0.10 ha–23.04 ha. The approach also gives an insight into seasonal water level changes. Based on an extensive quantification of error sources, we discuss how the results of the automated workflow can be further enhanced by incorporating additional information on weather conditions and image metadata and by improving the input database. The workflow is suitable for the seasonal to annual monitoring of lake changes on a sub-meter scale in the study areas in northern Alaska and can readily be scaled for application across larger regions within certain accuracy limitations.

Glacial Lakes Mapping Using Multi Satellite PlanetScope Imagery and Deep Learning

Glacial lakes mapping using satellite remote sensing data are important for studying the effects of climate change as well as for the mitigation and risk assessment of a Glacial Lake Outburst Flood (GLOF). The 3U cubesat constellation of Planet Labs offers the capability of imaging the whole Earth landmass everyday at 3–4 m spatial resolution. The higher spatial, as well as temporal resolution of PlanetScope imagery in comparison with Landsat-8 and Sentinel-2, makes it a valuable data source for monitoring the glacial lakes. Therefore, this paper explores the potential of the PlanetScope imagery for glacial lakes mapping with a focus on the Hindu Kush, Karakoram and Himalaya (HKKH) region. Though the revisit time of the PlanetScope imagery is short, courtesy of 130+ small satellites, this imagery contains only four bands and the imaging sensors in these small satellites exhibit varying spectral responses as well as lower dynamic range. Furthermore, the presence of cast shadows in the mountainous regions and varying spectral signature of the water pixels due to differences in composition, turbidity and depth makes it challenging to automatically and reliably extract surface water in PlanetScope imagery. Keeping in view these challenges, this work uses state of the art deep learning models for pixel-wise classification of PlanetScope imagery into the water and background pixels and compares the results with Random Forest and Support Vector Machine classifiers. The deep learning model is based on the popular U-Net architecture. We evaluate U-Net architecture similar to the original U-Net as well as a U-Net with a pre-trained EfficientNet backbone. In order to train the deep neural network, ground truth data are generated by manual digitization of the surface water in PlanetScope imagery with the aid of Very High Resolution Satellite (VHRS) imagery. The created dataset consists of more than 5000 water bodies having an area of approx. 71km2 in eight different sites in the HKKH region. The evaluation of the test data show that the U-Net with EfficientNet backbone achieved the highest F1 Score of 0.936. A visual comparison with the existing glacial lake inventories is then performed over the Baltoro glacier in the Karakoram range. The results show that the deep learning model detected significantly more lakes than the existing inventories, which have been derived from Landsat OLI imagery. The trained model is further evaluated on the time series PlanetScope imagery of two glacial lakes, which have resulted in an outburst flood. The output of the U-Net is also compared with the GLakeMap data. The results show that the higher spatial and temporal resolution of PlanetScope imagery is a significant advantage in the context of glacial lakes mapping and monitoring.

Tracking Lake and Reservoir Changes in the Nenjiang Watershed, Northeast China: Patterns, Trends, and Drivers

In terms of evident climate change and human activities, investigating changes in lakes and reservoirs is critical for sustainable protection of water resources and ecosystem management over the Nenjiang watershed (NJW), an eco-sensitive semi-arid region and the third-largest inland waterbody cluster in China. In this study, we established a multi-temporal dataset documenting lake and reservoir (area ≥ 1 km2) changes in this region using an object-oriented image classification method and Landsat series images from 1980 to 2015. Using the structural equation model (SEM), we analyzed the diverse impacts of climatic and anthropogenic variables on lake changes. Results indicated that lakes experienced significant changes with fluctuations over the past 35 years including obvious declines in the total area (by 42%) and number (by 51%) from 1980 to 2010 and a slight increase in the total lake area and number from 2010 to 2015. More than 235 lakes in the size class of 1–10 km2 decreased to small lakes (area < 1 km2), while 59 lakes covering 243.75 km2 disappeared. Total reservoir area and number had continuous increases during the investigated 35 years, with an areal expansion of 54.9% from 919 km2 to 1422 km2, and a number increase by 65.3% from 78 to 129. The SEM revealed that the lake area in the NJW had a significant correlation with the mean annual precipitation (MAP), suggesting that the MAP decline clarified most of the lake shrinkage in the NJW. Furthermore, agricultural consumption of water had potential impacts on lake changes, suggested by the significant relationship between cropland area and lake area.

A High-Resolution Airborne Color-Infrared Camera Water Mask for the NASA ABoVE Campaign

The airborne AirSWOT instrument suite, consisting of an interferometric Ka-band synthetic aperture radar and color-infrared (CIR) camera, was deployed to northern North America in July and August 2017 as part of the NASA Arctic-Boreal Vulnerability Experiment (ABoVE). We present validated, open (i.e., vegetation-free) surface water masks produced from high-resolution (1 m), co-registered AirSWOT CIR imagery using a semi-automated, object-based water classification. The imagery and resulting high-resolution water masks are available as open-access datasets and support interpretation of AirSWOT radar and other coincident ABoVE image products, including LVIS, UAVSAR, AIRMOSS, AVIRIS-NG, and CFIS. These synergies offer promising potential for multi-sensor analysis of Arctic-Boreal surface water bodies. In total, 3167 km2 of open surface water were mapped from 23,380 km2 of flight lines spanning 23 degrees of latitude and broad environmental gradients. Detected water body sizes range from 0.00004 km2 (40 m2) to 15 km2. Power-law extrapolations are commonly used to estimate the abundance of small lakes from coarser resolution imagery, and our mapped water bodies followed power-law distributions, but only for water bodies greater than 0.34 (±0.13) km2 in area. For water bodies exceeding this size threshold, the coefficients of power-law fits vary for different Arctic-Boreal physiographic terrains (wetland, prairie pothole, lowland river valley, thermokarst, and Canadian Shield). Thus, direct mapping using high-resolution imagery remains the most accurate way to estimate the abundance of small surface water bodies. We conclude that empirical scaling relationships, useful for estimating total trace gas exchange and aquatic habitats on Arctic-Boreal landscapes, are uniquely enabled by high-resolution AirSWOT-like mappings and automated detection methods such as those developed here.