TRAINING DATASET FOR THE MACHINE LEARNING APPROACH IN GLACIER MONITORING APPLYING SAR DATA

被引：0

作者：

Piwowar, Lukasz ^{[1
]}

Lucka, Magdalena ^{[1
]}

Witkowski, Wojciech ^{[1
]}

机构：

[1] AGH Univ Sci & Technol, Fac Geodata Sci Geodesy & Environm Engn, Aleja Mickiewicza 30, PL-30059 Krakow, Poland

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

关键词：

machine learning; synthetic training set; glacier motion; offset-tracking; Jakobshavn glacier; MOTION;

D O I：

10.1109/IGARSS52108.2023.10281675

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

The study analysed the possibility of utilizing machine learning to determine glacier displacements. The obtained results were compared with the offset-tracking method available in SNAP software. The Jakobshavn glacier in Greenland served as the test site. Analyses were carried out using Sentinel-1 data during the period of August 1 to August 7, 2021. To generate a dataset for the selected part of the glacier, a synthetic training dataset comprising 4,500 samples was created. It was constructed by applying rotation in the range of +/- 30 degrees and resizing within the range of +/- 10-20 pixels to the original patch. The final neural network (NN) consisted of 7 layers. The maximum displacement value is 250 m, corresponding to a velocity of 41 m/day. Notably, these maximum values are consistent with the results from offset-tracking. Nevertheless, the results in the slowly moving areas are not reliable because of the coarse resolution of the NN output.

引用

页码：191 / 194

页数：4

共 50 条

[21] A machine learning dataset for FRB detection in raw data
Xu, ZhiJun
An, Tao
Guo, ShaoGuang
Lao, BaoQiang
Lv, WeiJia
Wu, XiaoCong
SCIENTIA SINICA-PHYSICA MECHANICA & ASTRONOMICA, 2023, 53 (02)
[22] Runtime Data Layout Scheduling for Machine Learning Dataset
You, Yang
Demmel, James
2017 46TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING (ICPP), 2017, : 452 - 461
[23] Exploring the use of machine learning for interpreting electrochemical impedance spectroscopy data: evaluation of the training dataset size
Bongiorno, V.
Gibbon, S.
Michailidou, E.
Curioni, M.
CORROSION SCIENCE, 2022, 198
[24] A comparative study of a combinatorial machine learning approach to face detection using a very small training dataset
Oyarzo Huichaqueo, Marco
Magdaleno Maltas, Jordi
2021 IEEE CHILEAN CONFERENCE ON ELECTRICAL, ELECTRONICS ENGINEERING, INFORMATION AND COMMUNICATION TECHNOLOGIES (IEEE CHILECON 2021), 2021, : 709 - 715
[25] Evaluation of machine learning algorithms to Sentinel SAR data
Navale, Ashish
Haldar, Dipanwita
SPATIAL INFORMATION RESEARCH, 2020, 28 (03) : 345 - 355
[26] Evaluation of machine learning algorithms to Sentinel SAR data
Ashish Navale
Dipanwita Haldar
Spatial Information Research, 2020, 28 : 345 - 355
[27] DISTRIBUTED SAR DATA PROCESSING AIDED BY MACHINE LEARNING
D'Aria, Davide
Giudici, Davide
Persico, Adriano
Guccione, Pietro
Gerace, Fabio
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 7848 - 7851
[28] Backscattering signatures and techniques for snow and glacier monitoring using ERS-SAR and X-SAR data
Nagler, T
Rott, H
PROCEEDINGS OF THE EARSEL WORKSHOP ON REMOTE SENSING OF LAND ICE AND SNOW, 1997, : 121 - 121
[29] Optimizing data acquisition: a Bayesian approach for efficient machine learning model training
Mahani, M. R.
Nechepurenko, Igor A.
Rahimof, Yasmin
Wicht, Andreas
MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2024, 5 (03):
[30] kScore: a novel machine learning approach that is not dependent on the data structure of the training set
Oloff, Scott
Muegge, Ingo
JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN, 2007, 21 (1-3) : 87 - 95

← 1 2 3 4 5 →