Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches

Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method).

Tidal Correction Effects Analysis on Shoreline Mapping in Jepara Regency

The existence of high-spatial resolution imagery that are now available free by Planet Labs opens up opportunities in detailed scale mapping research, both as basic data and as reference data for geometry accuracy assessment. However, the use of several satellite sensors types with different recording times is the biggest obstacle in the use of high spatial resolution imagery as reference data because the shoreline instantaneous imaging at the data acquisition time does not consider the spatial and temporal variability of the shoreline boundaries. The purpose of this study was to analyze the effect of tidal correction on shoreline mapping in Jepara Regency using Landsat 8 OLI imagery in 2018.The effect of tidal correction analysis is done by comparing the position of the shoreline corrected by tides with the shoreline that is not corrected for tides. The influence of tidal correction is marked by differences in the position of the two shorelines. Shoreline shift calculation when there is a difference in tidal conditions between the test shoreline and the reference shoreline is carried out using the theory of right triangle (also called as one-line shift method).Based on the analysis of tidal correction effects, it is known that the shift in shoreline position after tidal correction varies from 0.21 m to 1.8 m, the value does not exceed one pixel of the PlanetScope image (3 m) so that tidal correction does not needs to be done because the effect is insignificant and undetectable on PlanetScope imagery. Keywords: tidal correction, shoreline, Planetscope, Landsat 8 OLI, Jepara