This paper applies a MaxEnt classification workflow to Sentinel-2 spectral bands and derived indices to map rooftops, non-intervened land, and intervened land across selected rural areas in Colombia and Chile. The study compares detected rooftop counts with housing-census counts and links the classification output to a photovoltaic screening tool. It identifies cloud cover, snow-related spectral confusion, and roof geometry as important constraints on wider application.
References
[1]
Lozano-Garzon, C., Bravo-Cordoba, G., Castro, H., Gonzalez-Rodriguez, G., Nino, D., Nunez, H., et al. (2022) Remote Sensing and Machine Learning Modeling to Support the Identification of Sugarcane Crops. IEEEAccess, 10, 17542-17555. https://doi.org/10.1109/access.2022.3148691
[2]
Pardo, C. (2020) Metodología para el monitoreo de cultivos a partir de imagenes satelitales con Machine Learning. Thesis Magister en Ingeniería de la Información, Universidad de los Andes.
[3]
Gouveia, N., Kephart, J.L., Dronova, I., McClure, L., Granados, J.T., Betancourt, R.M., et al. (2021) Ambient Fine Particulate Matter in Latin American Cities: Levels, Population Exposure, and Associated Urban Factors. ScienceoftheTotalEnvironment, 772, Article ID: 145035. https://doi.org/10.1016/j.scitotenv.2021.145035
[4]
Peyre, G., Lenoir, J., Karger, D.N., Gomez, M., Gonzalez, A., Broennimann, O., et al. (2020) The Fate of Páramo Plant Assemblages in the Sky Islands of the Northern Andes. JournalofVegetationScience, 31, 967-980. https://doi.org/10.1111/jvs.12898
[5]
Carroll Janer, I. and Jimenez, F. (2022) Land-Use Changes by Old Colonies Mennonites in Mexico with Sentinel 2 and Trends Earth. EuropeanJournalofAgricultureandFoodSciences, 4, 17-23. https://doi.org/10.24018/ejfood.2022.4.3.498
[6]
European Space Agency (2023) Sentinel-2 Data Collections. Copernicus Data Space Eco-System. https://dataspace.copernicus.eu/data-collections/copernicus-sentinel-missions/sentinel-2
[7]
Rouse, J.W., Haas, R.H., Schell, J.A. and Deering, D.W. (1973) Monitoring Vegetation Systems in the Great Plains with ERTS. Proceedings of the 3rd ERTS Symposium, Washington DC, 10-14 December 1973, 309-317.
[8]
McFeeters, S.K. (1996) The Use of the Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features. InternationalJournalofRemoteSensing, 17, 1425-1432. https://doi.org/10.1080/01431169608948714
[9]
Huete, A.R. (1988) A Soil-Adjusted Vegetation Index (SAVI). RemoteSensingofEnvironment, 25, 295-309. https://doi.org/10.1016/0034-4257(88)90106-x
[10]
Bannari, A., Morin, D., Bonn, F. and Huete, A.R. (1995) A Review of Vegetation Indices. RemoteSensingReviews, 13, 95-120. https://doi.org/10.1080/02757259509532298
[11]
Zha, Y., Gao, J. and Ni, S. (2003) Use of Normalized Difference Built-Up Index in Automatically Mapping Urban Areas from TM Imagery. InternationalJournalofRemoteSensing, 24, 583-594. https://doi.org/10.1080/01431160304987
[12]
Fernández, I.C. and Morales, N.S. (2019) One-Class Land-Cover Classification Using MaxEnt: The Effect of Modelling Parameterization on Classification Accuracy. PeerJ, 7, e7016. https://doi.org/10.7717/peerj.7016
[13]
Morales, N.S. and Fernández, I.C. (2020) Land-Cover Classification Using Maxent: Can We Trust in Model Quality Metrics for Estimating Classification Accuracy? Entropy, 22, Article No. 342. https://doi.org/10.3390/e22030342
[14]
Kabacoff, R. (2015) R in Action. 2nd Edition, Manning.
[15]
Crawley, M. (2013) The R Book. 2nd Edition, Wiley.
[16]
Departamento Administrativo Nacional de Estadística [DANE] (2019) Censo Nacional de Población y Vivienda 2018: Resultados y caracterización de la vivienda y el hogar en Colombia. DANE, Bogotá.
[17]
Instituto Nacional de Estadísticas [INE] (2018) Censo de Población y Vivienda 2017: Síntesis de resultados. Instituto Nacional de Estadísticas de Chile, Santiago.
