Arctic amplification has altered the climate patterns both regionally and globally, resulting in more frequent and more intense extreme weather events in the past few decades. The essential part of Arctic amplification is the unprecedented sea ice loss as demonstrated by satellite observations. Accurately forecasting Arctic sea ice from sub-seasonal to seasonal scales has been a major research question with fundamental challenges at play. In addition to physics-based Earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven approaches to study sea ice variations, we propose MT-IceNet – a UNet-based spatial and multi-temporal (MT) deep learning model for forecasting Arctic sea ice concentration (SIC). The model uses an encoder-decoder architecture with skip connections and processes multi-temporal input streams to regenerate spatial maps at future timesteps. Using bi-monthly and monthly satellite retrieved sea ice data from NSIDC as well as atmospheric and oceanic variables from ERA5 reanalysis product during 1979-2021, we show that our proposed model provides promising predictive performance for per-pixel SIC forecasting with up to 60% decrease in prediction error for a lead time of 6 months as compared to its state-of-the-art counterparts.
more »
« less
This content will become publicly available on May 1, 2024
Effects of Neural Network Architecture on Topography Estimation From Satellite Imagery for Multi-Terrain Autonomous Vehicle Path Planning and Control
Global warming is one of the world’s most pressing issues. The study of its effects on the polar ice caps and other arctic environments, however, can be hindered by the often dangerous and difficult to navigate terrain found there. Multi-terrain autonomous vehicles can assist researchers by providing a mobile platform on which to collect data in these harsh environments while avoiding any risk to human life and speeding up the research process. The mechanical design and ultimate efficacy of these autonomous robotic vehicles depends largely on the specific missions they are deployed for, but terrain conditions can vary wildly geographically as well as seasonally, making mission planning for these unmanned vehicles more difficult. This paper proposes the use of various UNet-based neural network architectures to generate digital elevation maps from satellite images, and explores and compares their efficacy on a single set of training and validation datasets generated from satellite imagery. These digital elevation maps generated by the model could be used by researchers not only to track the change in arctic topography over time, but to quickly provide autonomous exploratory research rovers with the topographical information necessary to decide on optimal paths during the mission. This paper analyzes different model architectures and training schemes: a traditional UNet, a traditional UNet with data augmentation, a UNet with a single active skip-layer vision transformer (ViT), and a UNet with multiple active skip-layer ViT. Each model was trained on a dataset of satellite images and corresponding digital elevation maps of Ellesmere Island, Canada. Utilizing ViTs did not demonstrate a significant improvement in UNet performance, though this could change with longer training. This paper proposes opportunities to improve performance for these neural networks, as well as next steps for further research, including improving the diversity of images in the dataset, generating a testing dataset from a completely different geographic location, and allowing the models more time to train.
more »
« less
- Award ID(s):
- 2116216
- NSF-PAR ID:
- 10451173
- Date Published:
- Journal Name:
- 2023 IEEE International Conference on Mobility, Operations, Services and Technologies (MOST)
- Page Range / eLocation ID:
- 124 to 131
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Accurate maps of regional surface water features are integral for advancing ecologic, atmospheric and land development studies. The only comprehensive surface water feature map of Alaska is the National Hydrography Dataset (NHD). NHD features are often digitized representations of historic topographic map blue lines and may be outdated. Here we test deep learning methods to automatically extract surface water features from airborne interferometric synthetic aperture radar (IfSAR) data to update and validate Alaska hydrographic databases. U-net artificial neural networks (ANN) and high-performance computing (HPC) are used for supervised hydrographic feature extraction within a study area comprised of 50 contiguous watersheds in Alaska. Surface water features derived from elevation through automated flow-routing and manual editing are used as training data. Model extensibility is tested with a series of 16 U-net models trained with increasing percentages of the study area, from about 3 to 35 percent. Hydrography is predicted by each of the models for all watersheds not used in training. Input raster layers are derived from digital terrain models, digital surface models, and intensity images from the IfSAR data. Results indicate about 15 percent of the study area is required to optimally train the ANN to extract hydrography when F1-scores for tested watersheds average between 66 and 68. Little benefit is gained by training beyond 15 percent of the study area. Fully connected hydrographic networks are generated for the U-net predictions using a novel approach that constrains a D-8 flow-routing approach to follow U-net predictions. This work demonstrates the ability of deep learning to derive surface water feature maps from complex terrain over a broad area.more » « less
-
The Native Village of Point Lay (Kali) on the North Slope of Alaska has been identified as the second-most permafrost thaw-affected community in the state of Alaska (Denali Commission, 2019). The village has 82 residential units, housing a population of approximately 330. There are several North Slope Borough municipal structures and the Kali School that serve the community. Most of the residential buildings in the village are built on an elevated surface underlain by ice-rich permafrost that is susceptible to thaw and terrain subsidence. This dataset consists of an orthomosaic and digital surface model (DSM) derived from drone surveys on 26 June 2022 in Point Lay, Alaska. 990 digital images were acquired from a DJI Phantom 4 Real-Time Kinematic (DJI P4RTK) quadcopter with a DJI D-RTK 2 Mobile Base Station. The mapped area was around 130 hectares (ha). The drone system was flown at 120 meters (m) above ground level (agl) and flight speeds varied from 7–8 meters/second (m/s). The orientation of the camera was set to 90 degrees (i.e. looking straight down). The along-track overlap and across-track overlap of the mission were set at 80 percent (%) and 70%, respectively. All images were processed in the software Pix4D Mapper (v. 4.7.5) using the standard 3D Maps workflow and the accurate geolocation and orientation calibration method to produce the orthophoto mosaic and digital surface model at spatial resolutions of 5 and 10 centimeters (cm), respectively. A Leica Viva differential global positioning system (GPS) provided ground control for the mission and the data were post-processed to WGS84 UTM Zone 5 North in Ellipsoid Heights (meters). Elevation information derived over waterbodies is noisy and does not represent the surface elevation of the feature.more » « less
-
Ice-rich permafrost is ground that is frozen all year round for two or more years and contains particularly large amounts of water that will be released upon thawing. This ice is the element of Arctic landscapes most susceptible to climate warming. Nearly 50% of the Arctic has ice-rich permafrost. For example, the upper 4-5 meters of the land along Alaska's northern coast contains an estimated 77% ice. Thawing of ice-rich permafrost affects entire arctic ecosystems and makes the ground unstable to build upon. This dataset consists of an orthomosaic and digital surface model (DSM) derived from drone surveys on 29 August 2021 at the Navigating the New Arctic, Ice-rich Permafrost Systems project field sites, in collaboration with the PermaSense project, in the Prudhoe Bay Oilfields. 2,463 digital images were acquired from a DJI Phantom 4 Real-Time Kinematic (DJI P4RTK) quadcopter with a DJI D-RTK 2 Mobile Base Station. The mapped area was around 232 hectares (ha). The drone system was flown at 100 meters (m) above ground level (agl) and flight speeds varied from 7–8 meters/second (m/s). The orientation of the camera was set to 90 degrees (i.e. looking straight down). The along-track overlap and across-track overlap of the mission were set at 80% and 70%, respectively. All images were processed in the software Pix4D Mapper (v. 4.6.4) using the standard 3D Maps workflow and the accurate geolocation and orientation calibration method to produce the orthophoto mosaic and digital surface model at spatial resolutions of 5 and 10 centimeters (cm), respectively. A Leica Viva differential global positioning system (GPS) provided ground control for the mission and the data were post-processed to WGS84 UTM Zone 6 North in Ellipsoid Heights (meters). Elevation information derived over waterbodies is noisy and does not represent the surface elevation of the feature.more » « less
-
Taken together, lakes and drained lake basins may cover up to 80% of the lowland landscapes in permafrost regions of the Arctic. Lake formation, growth, and drainage in lowland permafrost regions create a terrestrial and aquatic landscape mosaic of importance to geomorphic and hydrologic processes, tundra vegetation communities, permafrost and ground-ice characteristics, biogeochemical cycling, wildlife habitat, and human land-use activities. Our project focuses on quantifying the role of thermokarst lake expansion, drainage, and drained lake basin evolution in the Arctic System. We did this through a combination of field studies, environmental sensor networks, remote sensing, and modeling. This dataset consists of an orthomosaic and digital surface model (DSM) derived from drone surveys on 23 July 2022 at Derksen and Schmutz Basins on the Arctic Coastal Plain of northern Alaska. 6,158 digital images were acquired from a DJI Phantom 4 Real-Time Kinematic (DJI P4RTK) quadcopter with a DJI D-RTK 2 Mobile Base Station. The mapped area was around 580 hectares (ha). The drone system was flown at 100 meters (m) above ground level (agl) and flight speeds varied from 7–8 meters/second (m/s). The orientation of the camera was set to 90 degrees (i.e. looking straight down). The along-track overlap and across-track overlap of the mission were set at 80% and 70%, respectively. All images were processed in the software Pix4D Mapper (v. 4.8.4) using the standard 3D Maps workflow and the accurate geolocation and orientation calibration method to produce the orthophoto mosaic and digital surface model at spatial resolutions of 5 and 10 centimeters (cm), respectively. Elevation information derived over waterbodies is noisy and does not represent the surface elevation of the feature. A Leica Viva differential global positioning system (GPS) provided ground control for the mission and the data were post-processed to WGS84 UTM Zone 5 North in Ellipsoid Heights (meters).more » « less
