Estimating Surface Melt on the Larsen Ice Shelf Using a Deep Neural Network: Opportunities and Challenges

2021 ◽  
Author(s):  
Zhongyang Hu ◽  
Peter Kuipers Munneke ◽  
Stef Lhermitte ◽  
Maaike Izeboud ◽  
Michiel van den Broeke
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Neural Network ◽  
Climate Model ◽  
Climate Modeling ◽  
Coefficient Of Determination ◽  
Ice Shelf ◽  
Heterogeneous Terrain ◽  
Surface Melt ◽  
Larsen Ice Shelf

<p>Presently, surface melt over Antarctica is estimated using climate modeling or remote sensing. However, accurately estimating surface melt remains challenging. Both climate modeling and remote sensing have limitations, particularly in the most crucial areas with intense surface melt.  The motivation of our study is to investigate the opportunities and challenges in improving the accuracy of surface melt estimation using a deep neural network. The trained deep neural network uses meteorological observations from automatic weather stations (AWS) and surface albedo observations from satellite imagery to improve surface melt simulations from the regional atmospheric climate model version 2.3p2 (RACMO2). Based on observations from three AWS at the Larsen B and C Ice Shelves, cross-validation shows a high accuracy (root mean square error = 0.898 mm.w.e.d<sup>−1</sup>, mean absolute error = 0.429 mm.w.e.d<sup>−1</sup>, and coefficient of determination = 0.958). The deep neural network also outperforms conventional machine learning models (e.g., random forest regression, XGBoost) and a shallow neural network. To compute surface melt for the entire Larsen Ice Shelf, the deep neural network is applied to RACMO2 simulations. The resulting, corrected surface melt shows a better correlation with the AWS observations in AWS 14 and 17, but not in AWS 18. Also, the spatial pattern of the surface melt is improved compared to the original RACMO2 simulation. A possible explanation for the mismatch at AWS 18 is its complex geophysical setting. Even though our study shows an opportunity to improve surface melt simulations using a deep neural network, further study is needed to refine the method, especially for complicated, heterogeneous terrain.</p>

scholarly journals Improving Surface Melt Estimation over Antarctica Using Deep Learning: A Proof-of-Concept over the Larsen Ice Shelf

2021 ◽  
Author(s):  
Zhongyang Hu ◽  
Peter Kuipers Munneke ◽  
Stef Lhermitte ◽  
Maaike Izeboud ◽  
Michiel van den Broeke
Keyword(s):  
Deep Learning ◽  
Climate Model ◽  
High Surface ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Climate Modelling ◽  
Ice Shelf ◽  
Surface Melt ◽  
Mlp Model ◽  
Larsen Ice Shelf

Abstract. Accurately estimating surface melt volume of the Antarctic Ice Sheet is challenging, and has hitherto relied on climate modelling, or on observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate the potential of improving surface melt simulations by deploying a deep learning model. A deep-learning-based framework has been developed to correct surface melt from the regional atmospheric climate model version 2.3p2 (RACMO2), using meteorological observations from automatic weather stations (AWSs), and surface albedo from satellite imagery. The framework includes three steps: (1) training a deep multilayer perceptron (MLP) model using AWS observations; (2) correcting moderate resolution imaging spectroradiometer (MODIS) albedo observations, and (3) using these two to correct the RACMO2 surface melt simulations. Using observations from three AWSs at the Larsen B and C Ice Shelves, Antarctica, cross-validation shows a high accuracy (root mean square error = 0.95 mm w.e. per day, mean absolute error = 0.42 mm w.e. per day, and coefficient of determination = 0.95). Moreover, the deep MLP model outperforms conventional machine learning models (e.g., random forest regression, XGBoost) and a shallow MLP model. When applying the trained deep MLP model over the entire Larsen Ice Shelf, the resulting, corrected RACMO2 surface melt shows a better correlation with the AWS observations for two out of three AWSs. However, for one location (AWS 18) the deep MLP model does not show improved agreement with AWS observations, likely due to the heterogeneous drivers of melt within the corresponding coarse resolution model pixels. Our study demonstrates the opportunity to improve surface melt simulations using deep learning combined with satellite albedo observations. On the other hand, more work is required to refine the method, especially for complicated and heterogeneous terrains.

scholarly journals Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf

2021 ◽  
Vol 15 (12) ◽  
pp. 5639-5658
Author(s):  
Zhongyang Hu ◽  
Peter Kuipers Munneke ◽  
Stef Lhermitte ◽  
Maaike Izeboud ◽  
Michiel van den Broeke
Keyword(s):  
Deep Learning ◽  
Climate Model ◽  
Ice Sheet ◽  
Katabatic Wind ◽  
Ice Shelf ◽  
Antarctic Ice Sheet ◽  
Surface Melt ◽  
Mlp Model ◽  
The Antarctic ◽  
Larsen Ice Shelf

Abstract. Accurately estimating the surface melt volume of the Antarctic Ice Sheet is challenging and has hitherto relied on climate modeling or observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate the potential of improving surface melt simulations with a regional climate model by deploying a deep learning model. A deep-learning-based framework has been developed to correct surface melt from the regional atmospheric climate model version 2.3p2 (RACMO2), using meteorological observations from automatic weather stations (AWSs) and surface albedo from satellite imagery. The framework includes three steps: (1) training a deep multilayer perceptron (MLP) model using AWS observations, (2) correcting Moderate Resolution Imaging Spectroradiometer (MODIS) albedo observations, and (3) using these two to correct the RACMO2 surface melt simulations. Using observations from three AWSs at the Larsen B and C ice shelves, Antarctica, cross-validation shows a high accuracy (root-mean-square error of 0.95 mm w.e. d−1, mean absolute error of 0.42 mm w.e. d−1, and a coefficient of determination of 0.95). Moreover, the deep MLP model outperforms conventional machine learning models and a shallow MLP model. When applying the trained deep MLP model over the entire Larsen Ice Shelf, the resulting corrected RACMO2 surface melt shows a better correlation with the AWS observations for two out of three AWSs. However, for one location (AWS 18), the deep MLP model does not show improved agreement with AWS observations; this is likely because surface melt is largely driven by factors (e.g., air temperature, topography, katabatic wind) other than albedo within the corresponding coarse-resolution model pixels. Our study demonstrates the opportunity to improve surface melt simulations using deep learning combined with satellite albedo observations. However, more work is required to refine the method, especially for complicated and heterogeneous terrains.

scholarly journals OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data

2020 ◽  
Vol 12 (14) ◽  
pp. 2294
Author(s):  
Hua Su ◽  
Haojie Zhang ◽  
Xupu Geng ◽  
Tian Qin ◽  
Wenfang Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Network Architecture ◽  
Climate Changes ◽  
Heat Content ◽  
Remote Sensing Data ◽  
Ocean Heat Content ◽  
Global Ocean ◽  
Coefficient Of Determination ◽  
Sensing Data

Retrieving information concerning the interior of the ocean using satellite remote sensing data has a major impact on studies of ocean dynamic and climate changes; however, the lack of information within the ocean limits such studies about the global ocean. In this paper, an artificial neural network, combined with satellite data and gridded Argo product, is used to estimate the ocean heat content (OHC) anomalies over four different depths down to 2000 m covering the near-global ocean, excluding the polar regions. Our method allows for the temporal hindcast of the OHC to other periods beyond the 2005–2018 training period. By applying an ensemble technique, the hindcasting uncertainty could also be estimated by using different 9-year periods for training and then calculating the standard deviation across six ensemble members. This new OHC product is called the Ocean Projection and Extension neural Network (OPEN) product. The accuracy of the product is accessed using the coefficient of determination (R2) and the relative root-mean-square error (RRMSE). The feature combinations and network architecture are optimized via a series of experiments. Overall, intercomparison with several routinely analyzed OHC products shows that the OPEN OHC has an R2 larger than 0.95 and an RRMSE of <0.20 and presents notably accurate trends and variabilities. The OPEN product can therefore provide a valuable complement for studies of global climate changes.

scholarly journals Evaluating Deep Learning models for predicting ALK-5 inhibition

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0246126
Author(s):  
Gabriel Z. Espinoza ◽  
Rafaela M. Angelo ◽  
Patricia R. Oliveira ◽  
Kathia M. Honorio
Keyword(s):  
Neural Network ◽  
Biological Activity ◽  
Deep Learning ◽  
Deep Neural Network ◽  
External Validation ◽  
Machine Learning Techniques ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Learning Models ◽  
Alk 5

Computational methods have been widely used in drug design. The recent developments in machine learning techniques and the ever-growing chemical and biological databases are fertile ground for discoveries in this area. In this study, we evaluated the performance of Deep Learning models in comparison to Random Forest, and Support Vector Regression for predicting the biological activity (pIC50) of ALK-5 inhibitors as candidates to treat cancer. The generalization power of the models was assessed by internal and external validation procedures. A deep neural network model obtained the best performance in this comparative study, achieving a coefficient of determination of 0.658 on the external validation set with mean square error and mean absolute error of 0.373 and 0.450, respectively. Additionally, the relevance of the chemical descriptors for the prediction of biological activity was estimated using Permutation Importance. We can conclude that the forecast model obtained by the deep neural network is suitable for the problem and can be employed to predict the biological activity of new ALK-5 inhibitors.

Sign in / Sign up

Export Citation Format

Share Document