Kalani Randima Lakshani Pathira Arachchilage

Mrs. Kalani Randima Lakshani Pathira Arachchilage

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 June 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Indishe SenanayakeIndishe Senanayake
Indishe Senanayake
KAKalani Randima Lakshani Pathira Arachchilage
Kalani Randima Lakshani Pathira Arachchilage
In-Young YeoIn-Young Yeo
In-Young Yeo
Mehdi KhakiMehdi Khaki
Mehdi Khaki
SHShin-Chan Han
Shin-Chan Han
PDPeter Dahlhaus
Peter Dahlhaus
Soil moisture (SM) is a key variable driving hydrologic, climatic, and ecological processes. Although it is highly variable, both spatially and temporally, there is limited data availability to inform about SM conditions at adequate spatial and temporal scales over large regions. Satellite SM retrievals, especially L-band microwave remote sensing, has emerged as a feasible solution to offer spatially continuous global-scale SM information. However, the coarse spatial resolution of these L-band microwave SM retrievals poses uncertainties in many regional- and local-scale SM applications which require a high amount of spatial details. Numerous studies have been conducted to develop downscaling algorithms to enhance the spatial resolution of coarse-resolution satellite-derived SM datasets. Machine Learning (ML)-based downscaling models have gained prominence recently due to their ability to capture non-linear, complex relationships between SM and its driving factors, such as vegetation, surface temperature, topography, and climatic conditions. This review paper presents a comprehensive review of the ML-based approaches used in SM downscaling. The usage of classical, ensemble, neural nets, and deep learning methods to downscale SM products and the comparison of multiple algorithms are detailed in this paper. Insights into the significance of surface ancillary variables for model accuracy and the improvements made to ML-based SM downscaling approaches are also discussed. Overall, this paper provides useful insights for future studies on developing reliable, high-spatial-resolution SM datasets using ML-based algorithms.

19 August 2022 in Journal of Geospatial Surveying
Verified
Journal Article
Open access
PDF file
KAKalani Randima Lakshani Pathira Arachchilage
Kalani Randima Lakshani Pathira Arachchilage
DTDanling Tang
Danling Tang
JYJ. Yu
J. Yu
SWS. Wang
S. Wang
The improper management of plastic waste has become a silent killer in the marine ecosystem. The scientific evidence of plastic accumulated in marine biota and entering the food web have urged quick actions against the plastic pollution. The plastic detection algorithms developed using satellite images can proclaim emission, transportation, weathering and accumulation of plastic that is vital in eliminating them. This study developed an index to find floating marine harvested macro plastic within Sentinel 2 ACOLITE and Sen2Cor images. This index preserved the plastic information protected the plastic information and maximized the separation of them from the surrounding objects. The identified plastic pixels were analysed using scatter plots to discriminate plastic from non-plastic objects and to observe the characteristics. The index and the scatter plot analysis detected the plastic pixels with bottle percentages more than or equal to 14%. The plastic bags and the fishing nets required around 50% pixel percentage to be detected. The plastic pixels with 100% plastic coverage were located as a separate cluster in the scatter plots. Therefore, the accurate detection of plastic pixels using ACOLITE and Sen2Cor images depends on the pixel plastic percentage and plastic coverage. The Sen2cor images classified plastic pixels according to their pixel plastic percentage for two dates. However, this classification was not successful for other dates with aerosol, clouds and smooth sea surface conditions which made the plastic signal weak. The ACOLITE and Sen2Cor atmospheric corrections are not suitable for plastic detection when the plastic signal is weak.