Bolivar Morales
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bolivar Morales has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Monica Ballinas
Centro de Investigación en Ciencias de Información Geoespacial, A.C., Mexico City 14240, Mexico
2 shared publications - Manuel Esperon-Rodriguez
Hawkesbury Institute for the Environment, Western Sydney University
1 shared publication - Pablo López-Ramírez
Center for Research in Geospatial Information Sciences (CentroGeo), Mexico City, CDMX, Mexico
1 shared publication - Victor Luis Barradas
Laboratorio de Interacción Planta Atmosfera, Instituto de Ecología, Universidad Nacional Autónoma de México, Mexico City 04510, Mexico
1 shared publication
Latest Publications
- Open Access
Comparing Machine Learning Models for Predicting Stomatal Conductance in 15 Urban Tree Species in Mexico City
Stomatal conductance (gS) is a key driver of urban tree transpiration and heat mitigation potential, but few studies compare machine learning models for predicting gS across multiple species in cities. This study applies five machine learning models (XGBoost, Random Forest, Support Vector Machine [SVM], Neural Network, and Random Forest Adjusted) and two classical models (Multiple Linear Regression and Generalized Additive Model [GAM]) to predict gS for 15 dominant tree species in the urban forest of Mexico City using environmental variables (air temperature, vapor pressure deficit, photosynthetically active radiation, and leaf water potential). We trained the models on a dataset of 300 observations per species, with 70% for training, 20% for validation, and 10% for testing, and evaluated performance using RMSE, MAE, and R2. Overall, XGBoost, GAM and SVM consistently showed the highest predictive performance, with R2 values up to 0.997, while the Neural Network and Multiple Linear Regression performed poorly (R2 ≈ 0.10–0.65). Model performance varied substantially among species, with XGBoost performing best for seven species, GAM for four, and SVM for four. Our results demonstrate that tree species gS can be accurately predicted using machine learning models in urban forests; however, model choice should account for species differences in performance. We therefore recommend that practitioners consider ensemble approaches of multiple models, excluding only the Neural Network, when selecting predictors for individual species.
Open AccessComparing Machine Learning Models for Predicting Stomatal Conductance in 15 Urban Tree Species in Mexico City
Stomatal conductance (gS) is a key driver of urban tree transpiration and heat mitigation potential, but few studies compare machine learning models for predicting gS across multiple species in cities. This study applies five machine learning models (XGBoost, Random Forest, Support Vector Machine [SVM], Neural Network, and Random Forest Adjusted) and two classical models (Multiple Linear Regression and Generalized Additive Model [GAM]) to predict gS for 15 dominant tree species in the urban forest of Mexico City using environmental variables (air temperature, vapor pressure deficit, photosynthetically active radiation, and leaf water potential). We trained the models on a dataset of 300 observations per species, with 70% for training, 20% for validation, and 10% for testing, and evaluated performance using RMSE, MAE, and R2. Overall, XGBoost, GAM and SVM consistently showed the highest predictive performance, with R2 values up to 0.997, while the Neural Network and Multiple Linear Regression performed poorly (R2 ≈ 0.10–0.65). Model performance varied substantially among species, with XGBoost performing best for seven species, GAM for four, and SVM for four. Our results demonstrate that tree species gS can be accurately predicted using machine learning models in urban forests; however, model choice should account for species differences in performance. We therefore recommend that practitioners consider ensemble approaches of multiple models, excluding only the Neural Network, when selecting predictors for individual species.
- Open Access
- 29 January 2026
- Published by MDPI AG in Geographies
- Vol. 6 (1) , 12
Spatial–Temporal Analysis of PM2.5 Contamination, Thermal Pollution, and Population Social Backwardness in the Metropolitan Area of Mexico City
Atmospheric contamination and thermal pollution are two phenomena that impact negatively on the quality of life of residents in a city. Furthermore, exposure to these phenomena has a differential impact on socioeconomic strata, with the poorest being the most affected. Spatial and temporal analyses were conducted of PM2.5 pollution and air temperature, as well as socioeconomic variable. This characterization revealed that low-income people are more exposed to thermal pollution during the warm season with temperatures up to 32.6 °C, and to PM2.5 pollution with concentrations up to 205 µgm−3 during the cold season, focusing on the eastern part of the Metropolitan Area of Mexico City (MAMC). High temperatures can persist for up to 6 h, while PM2.5 concentrations can persist for up to 5 h. The social backwardness index is a fixed variable that can change in the long term and is related to thermal pollution. This study will allow us to understand social and environmental vulnerability and, thus, to develop an appropriate mitigation methodology for these two phenomena and their impact on human health, with special attention to environmental justice issues.
- 29 January 2026
- Published by MDPI AG in Geographies
- Vol. 6 (1) , 12
Open AccessSpatial–Temporal Analysis of PM2.5 Contamination, Thermal Pollution, and Population Social Backwardness in the Metropolitan Area of Mexico City
Atmospheric contamination and thermal pollution are two phenomena that impact negatively on the quality of life of residents in a city. Furthermore, exposure to these phenomena has a differential impact on socioeconomic strata, with the poorest being the most affected. Spatial and temporal analyses were conducted of PM2.5 pollution and air temperature, as well as socioeconomic variable. This characterization revealed that low-income people are more exposed to thermal pollution during the warm season with temperatures up to 32.6 °C, and to PM2.5 pollution with concentrations up to 205 µgm−3 during the cold season, focusing on the eastern part of the Metropolitan Area of Mexico City (MAMC). High temperatures can persist for up to 6 h, while PM2.5 concentrations can persist for up to 5 h. The social backwardness index is a fixed variable that can change in the long term and is related to thermal pollution. This study will allow us to understand social and environmental vulnerability and, thus, to develop an appropriate mitigation methodology for these two phenomena and their impact on human health, with special attention to environmental justice issues.