A spatiotemporal prediction model for light pollution in conservation areas using remote sensing datasets

• Published in: Decision Analytics Journal
• Main Author: Riza L.S.; Putra Z.A.Y.; Firdaus M.F.Y.; Trihutama F.Z.; Izzuddin A.; Utama J.A.; Samah K.A.F.A.; Herdiwijaya D.; NQZ R.A.; Mumpuni E.S.
• Format: Article
• Language: English
• Published: Elsevier Inc. 2023
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85173669087&doi=10.1016%2fj.dajour.2023.100334&partnerID=40&md5=06d8f8f56b0269ba11b42e638391f770

Artificial Light at Night (ALAN) significantly threatens protected areas from urbanization. As urbanization continues to grow, there is a need for forecasting future light pollution and ALAN for the protected areas in Indonesia. This study proposes a four-step computational model for forecasting spatial–temporal light pollution in nine protected areas in Indonesia via spatiotemporal modeling and linear models. The four steps for predicting spatial–temporal light pollution are (i) data collection, (ii) data pre-processing, (iii) model and prediction of population, and (iv) model and prediction of light pollution. Two critical data must be provided: population data from the review area and light pollution data generated by the Earth Observations Group (EOG) at the National Oceanic and Atmospheric Administration (NOAA)/National Centers for Environmental Information (NCEI). We are using nine conservation areas in Indonesia, including the Kuningan Botanical Gardens, Bosscha Observatory, Timau Kupang National Observatory, Sermo Reservoir, Mount Batur Geopark, Sewu Mountains Geopark, Mount Rinjani Geopark, Lake Toba Geopark, and Belitong Geopark. The developed model involves a linear model to predict ALAN with spatial–temporal modeling. We present long-term predictions for the next 20 years. © 2023 The Author(s)