High-resolution benthic habitat mapping from machine learning on PlanetScope imagery and ICESat-2 data

An, Nguyen Van; Quang, Nguyen Hao; Son, Tong Phuoc Hoang; An, Tran Thi

doi:10.1080/10106049.2023.2184875

Cited by 4 publications

(1 citation statement)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple studies confirmed the ability to retrieve bathymetry to ∼1 Secchi depth, or >40 m in very clear waters, with typical accuracies on the order of 0.5 m (Albright & Glennie, 2021; Chen et al., 2021; Le Quilleuc et al., 2022; Parrish et al., 2019; Ranndal et al., 2021; Watkins et al., 2023; Zhang et al., 2022). These bathymetric capabilities were soon shown to be of value for a wide range of science uses, from the study of coral reefs and other sensitive marine habitats to assessment of seafloor morphological change (Herrmann et al., 2022; Le Quilleuc et al., 2022; Selamat et al., 2021; Van An et al., 2023). One growing application is the fusion of ICESat‐2 bathymetric data with optical satellite imagery to create satellite derived bathymetry (SDB) maps in shallow coastal environments (Babbel et al., 2021; Cao et al., 2021; Ma et al., 2020; Thomas et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

Analysis of ICESat‐2 Data Acquisition Algorithm Parameter Enhancements to Improve Worldwide Bathymetric Coverage

Dietrich,

Rackley Reese,

Gibbons

et al. 2024

Earth and Space Science

View full text Add to dashboard Cite

A major advance in global bathymetric observation occurred in 2018 with the launch of NASA’s ICESat‐2 satellite, carrying a green‐wavelength, photon‐counting lidar, the Advanced Topographic Laser Altimeter System (ATLAS). Although bathymetric measurement was not initially a design goal for the mission, pre‐ and post‐launch studies revealed ATLAS’s notable bathymetric mapping capability. ICESat‐2 bathymetry has been used to support a wide range of coastal and nearshore science objectives. However, analysis of ICESat‐2 bathymetry in numerous locations around the world revealed instances of missing or clipped bathymetry in areas where bathymetric measurement should be feasible. These missing data were due to the ATLAS receiver algorithms not being optimized for bathymetry capture. To address this, two updates have been made to ICESat‐2’s receiver algorithm parameters with the goal of increasing the area for which ICESat‐2 can provide bathymetry. This paper details the parameter changes and presents the results of a two‐phased study designed to investigate ICESat‐2’s bathymetry enhancements at both local and global scales. The results of both phases confirm that the new parameters achieved the intended goal of increasing the amount of bathymetry provided by ICESat‐2. The site‐specific phase demonstrates the ability to fill critical bathymetric data gaps in open ocean and coastal settings. The global analysis shows that the area of potential bathymetry approximately doubled, with 6.1 million km2 of new area in which bathymetric measurements may be feasible. These enhancements are anticipated to facilitate a range of science objectives and close the gap between ICESat‐2 bathymetry and offshore sonar data.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of ICESat‐2 Data Acquisition Algorithm Parameter Enhancements to Improve Worldwide Bathymetric Coverage

Dietrich,

Rackley Reese,

Gibbons

et al. 2024

Earth and Space Science

View full text Add to dashboard Cite

show abstract

Global and local magnitude and spatial pattern of uncertainty from geographically adaptive empirical and machine learning satellite-derived bathymetry models

Lowell,

Rzhanov

2024

GIScience & Remote Sensing

View full text Add to dashboard Cite

Novel Learning of Bathymetry from Landsat 9 Imagery Using Machine Learning, Feature Extraction and Meta-Heuristic Optimization in a Shallow Turbid Lagoon

Tran,

Nguyen,

Pham

et al. 2024

Geosciences

View full text Add to dashboard Cite

Bathymetry data is indispensable for a variety of aquatic field studies and benthic resource inventories. Determining water depth can be accomplished through an echo sounding system or remote estimation utilizing space-borne and air-borne data across diverse environments, such as lakes, rivers, seas, or lagoons. Despite being a common option for bathymetry mapping, the use of satellite imagery faces challenges due to the complex inherent optical properties of water bodies (e.g., turbid water), satellite spatial resolution limitations, and constraints in the performance of retrieval models. This study focuses on advancing the remote sensing based method by harnessing the non-linear learning capabilities of the machine learning (ML) model, employing advanced feature selection through a meta-heuristic algorithm, and using image extraction techniques (i.e., band ratio, gray scale morphological operation, and morphological multi-scale decomposition). Herein, we validate the predictive capabilities of six ML models: Random Forest (RF), Support Vector Machine (SVM), CatBoost (CB), Extreme Gradient Boost (XGB), Light Gradient Boosting Machine (LGBM), and KTBoost (KTB) models, both with and without the application of meta-heuristic optimization (i.e., Dragon Fly, Particle Swarm Optimization, and Grey Wolf Optimization), to accurately ascertain water depth. This is achieved using a diverse input dataset derived from multi-spectral Landsat 9 imagery captured on a cloud-free day (19 September 2023) in a shallow, turbid lagoon. Our findings indicate the superior performance of LGBM coupled with Particle Swamp Optimization (R2 = 0.908, RMSE = 0.31 m), affirming the consistency and reliability of the feature extraction and selection-based framework, while offering novel insights into the expansion of bathymetric mapping in complex aquatic environments.

show abstract

High-resolution benthic habitat mapping from machine learning on PlanetScope imagery and ICESat-2 data

Cited by 4 publications

References 71 publications

Analysis of ICESat‐2 Data Acquisition Algorithm Parameter Enhancements to Improve Worldwide Bathymetric Coverage

Analysis of ICESat‐2 Data Acquisition Algorithm Parameter Enhancements to Improve Worldwide Bathymetric Coverage

Global and local magnitude and spatial pattern of uncertainty from geographically adaptive empirical and machine learning satellite-derived bathymetry models

Novel Learning of Bathymetry from Landsat 9 Imagery Using Machine Learning, Feature Extraction and Meta-Heuristic Optimization in a Shallow Turbid Lagoon

Contact Info

Product

Resources

About