Automated detection and tracking of medium-large icebergs from Sentinel-1 imagery using Google Earth Engine

Koo, YoungHyun; Xie, Hongjie; Mahmoud, H. Ahmed; Iqrah, Jurdana Masuma; Ackley, Stephen F.

doi:10.1016/j.rse.2023.113731

Cited by 10 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, however, most of these studies exploring XAI with GEE used only the built-in feature importance (MDI) of the random forest (RF) classifier. There are few studies that adopt permutation or SHAP feature importance to interpret the ML models used for land cover classification [22,30].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Land Cover Mapping and Monitoring: An Interactive and Explainable Machine Learning Approach Using Google Earth Engine

Chen,

Yang,

2023

Remote Sensing

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) have been applied to solve various remote sensing problems. To fully leverage the power of AI and ML to tackle impactful remote sensing problems, it is essential to enable researchers and practitioners to understand how AI and ML models actually work and thus to improve the model performance strategically. Accurate and timely land cover maps are essential components for informed land management decision making. To address the ever-increasing need for high spatial and temporal resolution maps, this paper developed an interactive and open-source online tool, in Python, to help interpret and improve the ML models used for land cover mapping with Google Earth Engine (GEE). The tool integrates the workflow of both land cover classification and land cover change dynamics, which requires the generation of a time series of land cover maps. Three feature importance metrics are reported, including impurity-based, permutation-based, and SHAP (Shapley additive explanations) value-based feature importance. Two case studies are presented to showcase the tool’s capability and ease of use, enabling a globally accessible and free convergent application of remote sensing technologies. This tool may inspire researchers to facilitate explainable AI (XAI)-empowered remote sensing applications with GEE.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing Land Cover Mapping and Monitoring: An Interactive and Explainable Machine Learning Approach Using Google Earth Engine

Chen,

Yang,

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…This stems from the complex interactions between ice forms and their subtle relationship to their surroundings. Simply transferring the ice form to a different scene may not yield real results 32 …”

Section: Related Workmentioning

confidence: 99%

An image augmentation‐based ice monitoring method for safe navigation of polar ships

Liang,

Wang,

Zhao

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

The navigation safety of polar ships depends on accurate monitoring of ice conditions along the route. Complex polar environments but scarce ice datasets pose challenges for deep learning‐based object detection methods. To address this issue, we propose an ice monitoring method based on polar environment adaptive image enhancement. This approach adaptively augments the ice dataset by simulating polar environments such as snowflakes and aurora to improve the training precision of ice detection models in harsh polar environments and meet the needs of safe navigation of polar ships. First, an image augmentation method based on randomly generated snowflake textures is proposed to address the difficulty of covering polar storm scenarios in existing ice datasets, which leads to weak generalization of ice monitoring models. Second, targeting the problem that the boundary between ice and background is confused by aurora phenomena, which severely reduces the ice monitoring accuracy, we propose an image augmentation method based on aurora simulations to improve the ice monitoring performance of trained models under aurora. Finally, an adaptive image augmentation strategy based on the brightness‐contrast threshold is proposed to optimize the snowflake density and aurora intensity in the augmented images to improve the discrimination of ice boundaries. Experimental results demonstrate the effectiveness of the proposed method, which improves the ice state detection accuracy from 0.640 to 0.950, thus providing a reliable guarantee for the safe navigation of polar ships.

show abstract

Global 24 solar terms phenological MODIS normalized difference vegetation index dataset in 2001–2022

Yang,

Wu,

Sun

et al. 2024

Geoscience Data Journal

View full text Add to dashboard Cite

Phenology reflects the life cycle of vegetation, crucial for monitoring global vegetation diversity, ecosystem stability, and agricultural security. However, there is currently no dataset related to phenology. The 24 solar terms (24STs), based on the Sun's annual motion, reflect the changing seasons, temperature fluctuations, and phenological phenomena. They serve as a vital means to characterize vegetation phenology. This study generate a global Normalized Difference Vegetation Index (NDVI) product based on 24STs using Moderate Resolution Imaging Spectroradiometer (MODIS) on the Google Earth Engine (GEE). The 24STs NDVI dataset adopted the maximum value compositing (MVC) to process the NDVI values between two adjacent 24STs. The product has a spatial resolution of 250 m, covering the period from 2001 to 2022. Comparing with the MOD13Q1, good spatiotemporal consistency between the two datasets was observed, confirming the reliability of the 24STs product. However, the 24STs product holds distinct phenological meanings. This product introduces, for the first time, a vegetation index dataset based on the 24STs, enriching the vegetation index dataset and facilitating further research on phenology.

show abstract

Automated detection and tracking of medium-large icebergs from Sentinel-1 imagery using Google Earth Engine

Cited by 10 publications

References 50 publications

Enhancing Land Cover Mapping and Monitoring: An Interactive and Explainable Machine Learning Approach Using Google Earth Engine

Enhancing Land Cover Mapping and Monitoring: An Interactive and Explainable Machine Learning Approach Using Google Earth Engine

An image augmentation‐based ice monitoring method for safe navigation of polar ships

Global 24 solar terms phenological MODIS normalized difference vegetation index dataset in 2001–2022

Contact Info

Product

Resources

About