Using machine learning algorithms to predict groundwater levels in Indonesian tropical peatlands.

Tropical peatlands play a vital role in the global carbon cycle as large carbon reservoirs and substantial carbon sinks. Indonesia possesses the largest share (65 %) of tropical peat carbon, equal to 57.4 Gt C. Human perturbations such as extensive logging, deforestation and canalization exacerbate water losses, especially during dry seasons, when low precipitation and high evapotranspiration rates combine with the increased drainage to lower groundwater levels. Drying and increasing temperatures of the surface peat exacerbate ignition and wildfire risks within the peat soils. As such, it is critically important to know how groundwater levels in peatlands are changing over space and time. In this study, a multilinear regression model as well as two machine learning algorithms, random forest and extreme gradient boosting, were used to model groundwater level over the study period (2010-12) within a peat dome impacted by drainage canals and multiple wildfires in Central Kalimantan, Indonesia. Although all three models performed well, based on overall fit, spatial modeling of groundwater level results revealed that extreme gradient boosting (R2 = 0.998, RMSE = 0.048 m) outperformed random forest (R2 = 0.997, RMSE = 0.054 m) and multilinear regression (R2 = 0.970, RMSE = 0.221 m) near drainage canals, which are key fire ignition risk locations in the peatlands. Our study also shows that, on average, elevation and precipitation are the most important parameters influencing groundwater level spatiotemporally.

Long-lead prediction of the 2015 fire and haze episode in Indonesia.

We conducted a case study of NCEP CFSv2 seasonal model forecast performance over Indonesia in predicting the dry conditions in 2015 that led to severe fire, in comparison to the non-El Niño dry season conditions of 2016. Forecasts of the Drought Code (DC) component of Indonesia's Fire Danger Rating System were examined across the entire Equatorial Asia region and for the primary burning regions within it. Our results show that early warning lead times of high observed DC in September and October 2015 varied considerably for different regions. High DC over Southern Kalimantan and Southern New Guinea were predicted with 180-day lead times, whereas Southern Sumatra had lead times of up to only 60 days, which we attribute to the absence in the forecasts of an eastward decrease in Indian Ocean SSTs. This case study provides the starting point for longer-term evaluation of seasonal fire danger rating forecasts over Indonesia.