Handout (2.6 MB)
In this study, the spatial and temporal patterns of water chemistry data are explored by leveraging current and long-term monitoring programs, and by integrating satellite remote sensing imagery to inform future research on watercolor change as an indicator of water quality beyond the selected sampling lakes through the Survey of Climate change and Adirondack Lake Ecosystems (SCALE) Pilot Program. The ALAP dataset, with sampling since 1998, is compiled for the 150 lakes, and Dissolved Organic Content (DOC) and Colored Dissolved Organic Matter (CDOM) are selected for comparison with several empirical algorithms using satellite observations. Surface reflectance data from Sentinel-2 satellite is used to compile a 7-year record to test several existing empirical algorithms as well as machine learning models to investigate the capabilities of satellites in understanding the water quality dynamics in lakes within the Adirondacks by validating trends with the existing field data.
While many studies develop predictive relationships between remotely sensed surface reflectance and water parameters, these relationships are often limited to a specific geographic region and have little applicability in other areas. In order to remotely monitor DOC, region-based relationships must be developed. The preliminary data analysis of several algorithms does not show a strong correlation for the represented ALAP lakes. However, they exhibit consistent long-term trends from 2016-2023 using Sentinel-2 surface reflectance data, suggesting lake color change in several sampled lakes.
Since different empirical algorithms performed differently for various lakes, a machine-learning approach that can learn the complex relation between the inputs and data types is applied. Several machine-learning techniques, including boosting and bagging, are employed to estimate DOC using different input features from satellite surface reflectance data. The model utilizes 70% of the data from each lake selected for training and 30% for testing performance. To find the best-performing model, we examined the impact of lake classification, atmospheric correction algorithms, and lake water depth on the model's performance. This analysis is performed on an openly accessible Python script on the Google Earth Engine Platform for processing cloud-based publicly available satellite observation data, and will allow the determination of DOC, CDOM, and water-color relationships over various lakes while also studying the impact of climate change within the larger Adirondack region.

