by Piyush Yadav, Shamsuddin Ladha, Shailesh Deshpande, Edward Curry
Abstract:
. Land use land cover changes (LULC) are generally modeled using multi-scale spatio-temporal variables. Recently, Markov Chain (MC) has been used to model LULC changes. However, the model is derived from the proportion of LULC observed over a given period and it does not account for temporal factors such as macro-economic, socio-economic, etc. In this paper, we present a richer model based on Hidden Markov Model (HMM), grounded in the common knowledge that economic, social and LULC processes are tightly coupled. We propose a HMM where LULC classes represent hidden states and temporal factors represent emissions that are conditioned on the hidden states. To our knowledge, HMM has not been used in LULC models in the past. We further demonstrate its integration with other spatio-temporal models such as Logistic Regression. The integrated model is applied on the LULC data of Pune district in the state of Maharashtra (India) to predict and visualize urban LULC changes over the past 14 years. We observe that the HMM integrated model has improved prediction accuracy as compared to the corresponding MC integrated model.
Reference:
Piyush Yadav, Shamsuddin Ladha, Shailesh Deshpande, Edward Curry, "Computational Model for Urban Growth Using Socioeconomic Latent Parameters", Chapter in The First International Workshop on Urban Reasoning, pp. 65-78, 2019.
Bibtex Entry:
@incollection{Yadav2018,
abstract = {. Land use land cover changes (LULC) are generally modeled using multi-scale spatio-temporal variables. Recently, Markov Chain (MC) has been used to model LULC changes. However, the model is derived from the proportion of LULC observed over a given period and it does not account for temporal factors such as macro-economic, socio-economic, etc. In this paper, we present a richer model based on Hidden Markov Model (HMM), grounded in the common knowledge that economic, social and LULC processes are tightly coupled. We propose a HMM where LULC classes represent hidden states and temporal factors represent emissions that are conditioned on the hidden states. To our knowledge, HMM has not been used in LULC models in the past. We further demonstrate its integration with other spatio-temporal models such as Logistic Regression. The integrated model is applied on the LULC data of Pune district in the state of Maharashtra (India) to predict and visualize urban LULC changes over the past 14 years. We observe that the HMM integrated model has improved prediction accuracy as compared to the corresponding MC integrated model.},
author = {Yadav, Piyush and Ladha, Shamsuddin and Deshpande, Shailesh and Curry, Edward},
booktitle = {The First International Workshop on Urban Reasoning},
doi = {10.1007/978-3-030-13453-2_6},
file = {:Users/ed/Library/Application Support/Mendeley Desktop/Downloaded/Yadav et al. - 2019 - Computational Model for Urban Growth Using Socioeconomic Latent Parameters.pdf:pdf},
pages = {65--78},
title = {{Computational Model for Urban Growth Using Socioeconomic Latent Parameters}},
url = {http://edwardcurry.org/publications/Yadav2019_Chapter_ComputationalModelForUrbanGrow.pdf},
year = {2019}
}