气候变化领域集成服务门户(CCPortal): A trained Mask R-CNN model over PlanetScope imagery for very-high resolution surface water mapping in boreal forest-tundra

CCPortal

DOI	10.1016/j.rse.2024.114047
	A trained Mask R-CNN model over PlanetScope imagery for very-high resolution surface water mapping in boreal forest-tundra
	Freitas, Pedro; Vieira, Goncalo; Canario, Joao; Vincent, Warwick F.; Pina, Pedro; Mora, Carla
发表日期	2024
ISSN	0034-4257
EISSN	1879-0704
起始页码	304
卷号	304
英文摘要	Small water bodies (< 0.01 km(2)) showing diverse limnological properties occur in great abundance across the boreal forest and tundra landscapes of the Arctic and Subarctic. However, their classification, geographical distribution and collective importance for water, heat, nutrient, contaminant and carbon cycles are still poorly constrained. One important step for better understanding the role and evolution of small water bodies in the fastchanging northern landscapes is to develop image analysis protocols that allow their automatic remote sensing detection, delineation and inventory. In this study, we set an image analysis protocol (High Latitude Water - HLWATER V1.0) based on a trained supervised Mask R-CNN deep learning model over PlanetScope imagery for the automatic detection and delineation of small lakes and ponds that were absent in existing datasets. Most of our training dataset comprised water bodies smaller than 0.01 km(2) (97%) and spanned a wide range of environmental and hydrological settings, from the sporadic to the continuous permafrost zones of Canada. The model was tested as a fully autonomous approach for eastern Hudson Bay, Nunavik (Subarctic Canada), a region that poses challenges for water remote sensing given the abundance and variety of small water bodies. These are mainly permafrost thaw and glacial basin ponds in the boreal forest-tundra in challenging optical settings influenced by vegetation or topography shadowing, or revealing peat water logging, fen and bog pond conditions. A multi-scale validation approach was developed using water body delineations from PlanetScope imagery and ultra-high resolution orthomosaics from Unoccupied Aerial Systems. This procedure allowed a sub-pixel assessment and identified the limitations and strengths of the trained model for detecting small and large water bodies. The results varied according to different landscape units, with mean Intersection over Union (IoU) 0.5 F1 Scores of 0.53 to 0.71 and mean F1 Scores of 0.62 to 0.95. Considering 166 m(2) as the minimum pond size detection threshold, the IoU 0.5 F1 Scores were 0.7 to 0.91 and F1 Scores were 0.76 to 0.83, evaluated by comparing the model results with ultra-high resolution manual delineations. The image analysis protocol and trained model show high potential for extension to other boreal forest-tundra regions of the Arctic and Subarctic, allowing for detailed inventories of optically and morphologically diverse small water bodies over large areas of the circumpolar North.
英文关键词	Mask R-CNN; Deep learning; PlanetScope; Arctic and subarctic; Water mapping; Small water bodies
语种	英语
WOS研究方向	Environmental Sciences & Ecology ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Environmental Sciences ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:001186987600001
来源期刊	REMOTE SENSING OF ENVIRONMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/306381
作者单位	Universidade de Lisboa; Laval University; Universidade de Lisboa; Universidade de Lisboa; Laval University; Universidade de Coimbra; Universidade de Coimbra; Universidade de Lisboa
推荐引用方式 GB/T 7714	Freitas, Pedro,Vieira, Goncalo,Canario, Joao,et al. A trained Mask R-CNN model over PlanetScope imagery for very-high resolution surface water mapping in boreal forest-tundra[J],2024,304.
APA	Freitas, Pedro,Vieira, Goncalo,Canario, Joao,Vincent, Warwick F.,Pina, Pedro,&Mora, Carla.(2024).A trained Mask R-CNN model over PlanetScope imagery for very-high resolution surface water mapping in boreal forest-tundra.REMOTE SENSING OF ENVIRONMENT,304.
MLA	Freitas, Pedro,et al."A trained Mask R-CNN model over PlanetScope imagery for very-high resolution surface water mapping in boreal forest-tundra".REMOTE SENSING OF ENVIRONMENT 304(2024).