Surabaya is a coastal city that is still developing. Like other developing cities, Surabaya highly suppresses mangrove forests for residential, industrial, and other areas. Mangrove forests supply oxygen for the population of Surabaya. Forest mangroves reduce the effects of global warming and preserve sustainable coastal ecosystems. This research aimed to (1) map temperature changes in Surabaya over a period of 20 years (1996–2016) by using remote sensing and GIS, and (2) examine mangrove forests’ ability to absorb CO2 and decrease the impact of global warming in Surabaya. Research results showed that: (1) on the basis of the analysis of the temperature surface area, temperatures changed significantly between 1996 and 2016. Temperature changes can be classified into low, moderate, or high. The low-temperature area of 21–30 °C followed a different pattern. Each year, changes in the high-surface-temperature area were in the range of 31–42 °C. Changes highly increased in the period of 2006–2016. This indicates that Surabaya experienced a significant temperature increase in 2016. (2) There was correlation between the change in mangrove forest cover and the change in temperature; CO2 concentration in mangrove, vegetation, and water areas decreased as it grew in areas used for construction, such as factories, residences, and roads. CO2 concentration in Surabaya showed a distribution in the “high” and “extremely high” categories. The high category was 27.5%, and the extremely high category was 67.5%. The sample point in both the moderate and low category was around 25%.

The reliance on native MODIS-16 PET potential evapotranspiration (PET) in scarce-data-driven areas is growing in support among ecohydrological studies, yet information about its performance is limited or unknown as validation studies are mostly concentrated in developed countries. This study aimed to assess its performance at the monthly level using four ground measurements in a tropical watershed system with complex topography, applying a machine learning artificial neural network (ANN) to improve the estimates, and using the ANN-adjusted MODIS-16 PET to characterize the spatio-temporal patterns of PET in the Brantas watershed, as well as to understand the monthly patterns of water deficiency in areas under eight different vegetation covers. The results showed that the native MODIS-16 PET experienced overestimation with an RMSE of 37–66 mm/month and NRSME of up to 33%. The performance decreased in drier periods. The ANN-based adjustment using only one variable showed improved estimates with a reduction of RSME to only 14 mm and lower than 10% NRMSE. Sari-temporal patterns of PET in the Brantas watershed showed that the PET characteristics were not uniform. The southern part of the Brantas watershed has areas with relatively lower PET that are, thus, more prone to water deficiency. Complex topography and climate gradients within the watershed apparently became the multi-controllers of PET variations. The difference in vegetation cover also influenced the magnitudes of water deficiency.