Satellite-based Long-term Chl-a of Lake Balaton (hdl:21.15109/ARP/ZIJEIN)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Satellite-based Long-term Chl-a of Lake Balaton

hdl:21.15109/ARP/ZIJEIN

ARP

2025-06-02

1

Li, Huan, 2025, "Satellite-based Long-term Chl-a of Lake Balaton", https://hdl.handle.net/21.15109/ARP/ZIJEIN, ARP, V1

Satellite-based Long-term Chl-a of Lake Balaton

hdl:21.15109/ARP/ZIJEIN

Li, Huan

ARP

Li, Huan

Li, Huan

2025-06-02

https://hdl.handle.net/21.15109/ARP/ZIJEIN

Earth and Environmental Sciences

Chlorophyll-a (Chl-a) is one of the critical water quality indicators that shows the eutrophication status of aquatic ecosystems. As the largest lake and a well-known attraction in middle Europe, Lake Balaton contributes 70% or more of local economy through tourism, while also maintaining a unique biodiversity. Therefore, long-term monitoring of water quality is essential for its effective management. With the longest global environmental record and a preferable spatial resolution, the satellite constellation Landsat is used for retrieving Chl-a in this study. However, the common low-frequent in-situ samplings and ~16-day revisit of Landsat have limited both the quality and applicability of Landsat to Chl-a retrieval. Initially, we trained both linear and several machine learning models using matchups between in-situ measurements and satellite data from Landsat 4-9 missions during 1984 and 2023. To address the imbalanced data problem, which lacks high concentration samples due to the rare blooming events, we extend the time tolerance, incorporate temporal information, which connotes the phenology information, and apply an oversampling technique during the training process. Validated on Lake Balaton, which has a spatiotemporal amplitude of Chl-a concentration ranging from 5 to 260 µg/L since 1980s, Random Forest model has the best accuracy, which shows an R-square 0.86 and RMSE 8.16 μg/L. The oversampling technique improves the accuracy by 14% than the non-oversampled. Leveraging all strategies improves overall accuracy by 21%. The result also shows a reasonable trade-off via increasing the number of matchups 3 to 8 times by extending the time tolerance from the same day to 3 days regardless of the high variability of Chl-a due to the sinking and floating movement of algae. The enhancement framework can be applied to other lakes, especially for lakes with coarse samplings and wide Chl-a fluctuations. We present an open-source online tool for historical and real-time Chl-a mapping, designed for both experts and the public. With customizable code for global lakes, results are continuously showcased on the HUN-REN Balaton Limnological Research Institute's website and social media. If this repository is useful for you, please consider cite the work: Li, H., Somogyi, B., Chen, X., Luo, Z., Blix, K., Wu, S., Duan, Z. and Tóth, V.R. (2025) Leveraging Landsat and Google Earth Engine for Long-term Chlorophyll-a Monitoring: a Case Study of Lake Balaton’s water quality . Ecological Informatics.

Label:

Chl-a 1980s.tif

Text:

Average Chl-a map of Lake Balaton during 1980s

image/tiff

Label:

Chla_01-05.tif

Text:

Average Chl-a map of Lake Balaton from 2001 to 2005

image/tiff

Label:

Chla_06-10.tif

Text:

Average Chl-a map of Lake Balaton from 2006 to 2010

image/tiff

Label:

Chla_11-18.tif

Text:

Average Chl-a map of Lake Balaton from 2011 to 2018

image/tiff

Label:

Chla_19-23.tif

Text:

Average Chl-a map of Lake Balaton from 2019 to 2023

image/tiff

Label:

Chla_91-95.tif

Text:

Average Chl-a map of Lake Balaton from 1991 to 1995

image/tiff

Label:

Chla_96-00.tif

Text:

Average Chl-a map of Lake Balaton from 1996 to 2000

image/tiff

Label:

getSR_allLandsat.js

Text:

This is a crucial helper script, modified from a common GEE LandTrendr utility. It is responsible for fetching, preprocessing, and harmonizing Landsat 4, 5, 7, 8, and 9 Surface Reflectance (SR) collections. Functions include scaling SR values, renaming bands for consistency, and applying cloud, shadow, and snow masks. The getCombinedSRcollection function is extensively used by the other applications to acquire analysis-ready SR data.

text/javascript

Label:

OnlineApp.js

Text:

Visualizes long-term Chl-a trends in Lake Balaton from the 1980s to the present. It allows for the comparison of Chl-a concentrations across different decades. https://lihuan.projects.earthengine.app/view/chla-balaton

text/javascript

Label:

OnlineApp_history.js

Text:

Purpose: Allows users to visualize historical Chl-a maps for Lake Balaton on specific dates. Features: Split-panel interface to compare Chl-a maps from two user-selected historical dates (before and after 2005 by default). Selection of specific dates from available Landsat imagery. Time-series chart generation for Chl-a at clicked locations. Includes an "Adaptation Guide for Other Lakes" in its comments for users wishing to apply the script elsewhere. To Run: Copy the code from OnlineApp_history.js into the GEE Code Editor.

text/javascript

Label:

OnlineApp_realtime.js

Text:

Purpose: Provides near real-time Chl-a monitoring for Lake Balaton, focusing on imagery from the latest month. Features: Displays Chl-a maps derived from the most recent Landsat 8/9 imagery (typically within the last month). Users can select specific dates from the recent period to view corresponding Chl-a maps. Click-based inspection of Chl-a concentration values on the map. Utilizes a Random Forest model for Chl-a prediction. Includes an "Adaptation Guide for Other Lakes" in its comments. To Run: Copy the code from OnlineApp_realtime.js into the GEE Code Editor.

text/javascript

Label:

RF.txt

Text:

Random forest model

text/plain

Label:

visualize_SR_timeseries.js

Text:

visualize_SR_timeseries.js - Landsat Surface Reflectance Time Series Viewer Purpose: A utility to inspect and visualize raw Landsat (4-9) surface reflectance (SR) time series data for any clicked location globally. Features: Generates interactive charts for multiple Landsat bands (Blue, Green, Red, NIR, SWIR1, SWIR2). Allows comparison of SR values across different Landsat sensors (L4, L5, L7, L8, L9). Useful for data validation, understanding spectral signatures, or detailed spectral analysis. To Run: Copy the code from visualize_SR_timeseries.js into the GEE Code Editor.

text/javascript