Monitoring and Predictive Estimations of Atmospheric Parameters in the Catchment Area of Lake Baikal

Abstract

The paper is concerned with a methodological approach to monitoring the state of atmospheric parameters in the catchment area of Lake Baikal, including real-time analysis of actual distributed data with the determination of analog years according to the preset proximity of comparative indicators and the most probable long-term predictive distributions of surface temperatures, precipitation, pressure, and geopotential with a lead time of up to 9–12 months. We have developed the information-analytical system GeoGIPSAR to conduct the real-time analysis of spatial and point data by various processing methods and obtain long-term prognostic estimates of water inflow into the lake.

A Technology for Predictive Estimation of Meteorological Parameters on the Basis of the Global Climate Model CFSv2

“…It includes the tools for adding new components and developing the existing ones. The main component aims to obtain the most probable distributions of atmospheric processes for an arbitrary time period [11,12].…”

Sistema de alerta temprana de inundaciones para el río Arauca basado en técnicas de inteligencia artificial

“…2.2 Modelos matemáticos del río El tratamiento de la información para desarrollar sistemas de alertas tempranas lleva consigo la aplicación de métodos de pronóstico hidrológicos, generalmente regresiones lineales (Abasov et al, 2022). Estos métodos establecen relaciones entre variables dependientes e independientes del fenómeno, a partir de variables de entrada, como precipitación y nivel, y variables de salida como el caudal (Cai & Yu, 2022).…”

“…Seguidamente, se realiza el tratamiento de normalización y a partir de los módulos estructurados, se usan técnicas inteligentes. Entre estas técnicas se tienen las Redes Neuronales (RN) y las neuro-difusas (ANFIS), así como el Algoritmo de redes neuronales (ALG), que permite variar parámetros como: número de neuronas, número de capas, funciones de activación, distribución de datos en el entrenamiento, validación y prueba (Abasov et al, 2022). En la Figura 6 se comparan los modelos diseñados, que definen la tendencia del modelo matemático de caudal del río en el municipio de Arauca.…”

Prognostic Maps of Climatic Indicators Based on a Multivariate Neural Network

“…The Institute has developed the GeoGIPSAR system for the long-term predictive estimation of water inflow and the climatic situation, which relies on probabilistic, approximative, and other methods for long-term estimation. Recently, neural network approaches have been used to make a long-term forecast [13][14][15] considering the global climate changes. A multivariate neural network (MNN) with a variety of settings (changing the number of hidden layers and a set of neurons in a layer, the type of activation function in a neuron, etc.)…”

“…Interval estimates can increase the probability of predictive indicators, but are not sufficient to obtain guaranteed results. To increase the probability, the paper presents an approach to the creation of predictive climate maps for precipitation, temperature and other conditions to eliminate disagreement with interval estimates and other methods, for example, forecasting based on global climate models (CFSv2) [11,12,15,16].…”