2026 , Volume 31, № 5, p.128-144

This article presents the “Baikal” information system, designed for comprehensive monitoring of the condition of Lake Baikal’s waters through the integration of satellite and field data. The relevance of this work stems from the need to create a domestic tool that fills the gap in specialized platforms for the real-time analysis of environmental parameters of the world’s largest freshwater body, given limited access to foreign services. The objective of this study is to develop a web-based system that provides centralized storage, visualization, automatic updating, and interactive analysis of multi-year time series (from 2000 to the present) of key water surface characteristics: water surface temperature (LSWT), chlorophyll a concentration, transparency, and others.

The novelty and uniqueness of the system lie in its hybrid architecture, which combines a local repository of pre-calculated products with cloud computing on the Google Earth Engine platform. This approach allows users to work in two modes: to gain instant access to pre-calculated monthly map charts or to independently generate online products for any polygon and time interval without any programming skills. Data processing is performed using data from the MODIS/(Terra+Aqua), VIIRS/Suomi NPP, (OLI, TIRS)/Landsat, OLCI/Sentinel-3, and MSI/Sentinel-2. Special attention is given to integrating in situ measurements from weather stations and ship-based expeditions (temperature, atmospheric pressure, wind speed, and water clarity), which provides the basis for calibrating and verifying satellite algorithms adapted for the optically complex waters of Lake Baikal.

The paper comprehensively describes a role-based access model, interactive cartographic visualization with clustering of observation points and the ability to select polygons, mechanisms for constructing time series, and exporting results in GeoTIFF, CSV, and XLS formats. Automated ETL processes ensure that the archives remain up-to-date in near real time.

The practical significance of this work lies not only in the creation of an effective tool for scientific research and management decision-making in the field of aquatic ecosystem conservation, but also in the development of a prototype for scaling this architecture to other large water bodies in Russia. Future developments for the system include the implementation of machine learning methods for forecasting time series and detecting anomalies, as well as expanding the range of satellite products analyzed.