Accession Number : ADA290081
Title : Forecasting Global Temperature Variations by Neural Networks.
Descriptive Note : Memorandum rept.,
Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
Personal Author(s) : Miyano, Takaya ; Girosi, Federico
PDF Url : ADA290081
Report Date : AUG 1994
Pagination or Media Count : 12
Abstract : Global temperature variations between 1861 and 1984 are forecast using regularization networks, multilayer perceptrons and linear autoregression. The regularization network, optimized by stochastic gradient descent associated with colored noise, gives the best forecasts. For all the models, prediction errors noticeably increase after 1965. These results are consistent with the hypothesis that the climate dynamics is characterized by low-dimensional chaos and that the it may have changed at some point after 1965, which is also consistent with the recent idea of climate change. (MM)
Descriptors : *NEURAL NETS, *ATMOSPHERIC TEMPERATURE, *WEATHER FORECASTING, STOCHASTIC PROCESSES, CHAOS, REGRESSION ANALYSIS, CLIMATE.
Subject Categories : Meteorology
Distribution Statement : APPROVED FOR PUBLIC RELEASE