Artificial intelligence for geoscience: Progress, challenges and perspectives

T Zhao, S Wang, C Ouyang, M Chen, C Liu, J Zhang… - The Innovation, 2024 - cell.com
This paper explores the evolution of geoscientific inquiry, tracing the progression from
traditional physics-based models to modern data-driven approaches facilitated by significant …

Using deep learning to map retrogressive thaw slumps in the Beiluhe region (Tibetan Plateau) from CubeSat images

L Huang, J Luo, Z Lin, F Niu, L Liu - Remote Sensing of Environment, 2020 - Elsevier
Retrogressive thaw slumps (RTSs) are among the most dynamic landforms in permafrost
areas, and their formation can be attributed to the thawing of ice-rich permafrost. The spatial …

Quantification of microtopography in natural ecosystems using close-range remote sensing

T Shukla, W Tang, CC Trettin, G Chen, S Chen… - Remote Sensing, 2023 - mdpi.com
Microtopography plays an important role in various ecological, hydrologic, and
biogeochemical processes. However, quantifying the characteristics of microtopography …

Develo** and testing a deep learning approach for map** retrogressive thaw slumps

I Nitze, K Heidler, S Barth, G Grosse - Remote Sensing, 2021 - mdpi.com
In a warming Arctic, permafrost-related disturbances, such as retrogressive thaw slumps
(RTS), are becoming more abundant and dynamic, with serious implications for permafrost …

[HTML][HTML] Transferability of the deep learning mask R-CNN model for automated map** of ice-wedge polygons in high-resolution satellite and UAV images

W Zhang, AK Liljedahl, M Kanevskiy, HE Epstein… - Remote Sensing, 2020 - mdpi.com
State-of-the-art deep learning technology has been successfully applied to relatively small
selected areas of very high spatial resolution (0.15 and 0.25 m) optical aerial imagery …

[HTML][HTML] Accuracy, efficiency, and transferability of a deep learning model for map** retrogressive thaw slumps across the Canadian Arctic

L Huang, TC Lantz, RH Fraser, KF Tiampo, MJ Willis… - Remote Sensing, 2022 - mdpi.com
Deep learning has been used for map** retrogressive thaw slumps and other periglacial
landforms but its application is still limited to local study areas. To understand the accuracy …

Rapid transformation of tundra ecosystems from ice-wedge degradation

MT Jorgenson, MZ Kanevskiy, JC Jorgenson… - Global and Planetary …, 2022 - Elsevier
Ice wedges are a common form of massive ground ice that typically occupy 10–30% of the
volume of upper permafrost in the Arctic and are particularly vulnerable to thawing from …

Understanding the synergies of deep learning and data fusion of multispectral and panchromatic high resolution commercial satellite imagery for automated ice …

C Witharana, MAE Bhuiyan, AK Liljedahl… - ISPRS Journal of …, 2020 - Elsevier
The utility of sheer volumes of very high spatial resolution (VHSR) commercial imagery in
map** the Arctic region is new and actively evolving. Commercial satellite sensors …

[HTML][HTML] A quantitative graph-based approach to monitoring ice-wedge trough dynamics in polygonal permafrost landscapes

T Rettelbach, M Langer, I Nitze, B Jones, V Helm… - Remote Sensing, 2021 - mdpi.com
In response to increasing Arctic temperatures, ice-rich permafrost landscapes are
undergoing rapid changes. In permafrost lowlands, polygonal ice wedges are especially …

[HTML][HTML] Understanding the effects of optimal combination of spectral bands on deep learning model predictions: a case study based on permafrost Tundra landform …

MAE Bhuiyan, C Witharana, AK Liljedahl, BM Jones… - Journal of …, 2020 - mdpi.com
Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in
very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer …