Estimation of Poverty Using Random Forest Regression with Multi-Source Data: A Case Study in Bangladesh

Abstract

Spatially explicit and reliable data on poverty is critical for both policy makers and researchers. However, such data remain scarce particularly in developing countries. Current research is limited in using environmental data from different sources in isolation to estimate poverty despite the fact that poverty is a complex phenomenon which cannot be quantified either theoretically or practically by one single data type. This study proposes a random forest regression (RFR) model to estimate poverty at 10 km × 10 km spatial resolution by combining features extracted from multiple data sources, including the National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) Day/Night Band (DNB) nighttime light (NTL) data, Google satellite imagery, land cover map, road map and division headquarter location data. The household wealth index (WI) drawn from the Demographic and Health Surveys (DHS) program was used to reflect poverty level. We trained the RFR model using data in Bangladesh and applied the model to both Bangladesh and Nepal to evaluate the model’s accuracy. The results show that the R2 between the actual and estimated WI in Bangladesh is 0.70, indicating a good predictive power of our model in WI estimation. The R2 between actual and estimated WI of 0.61 in Nepal also indicates a good generalization ability of the model. Furthermore, a negative correlation is observed between the district average WI and the poverty head count ratio (HCR) in Bangladesh with the Pearson Correlation Coefficient of -0.6. Using Gini importance, we identify that proximity to urban areas is the most important variable to explain poverty which contribute to 37.9% of the explanatory power. Compared to the study that used NTL and Google satellite imagery in isolation to estimate poverty, our method increases the accuracy of estimation. Given that the data we use are globally and publicly available, the methodology reported in this study would also be applicable in other countries or regions to estimate the extent of poverty.

Investigating the Potential of Using POI and Nighttime Light Data to Map Urban Road Safety at the Micro-Level: A Case in Shanghai, China

“…This indicates that the model may have a tendency to underestimate the higher values and overestimate the lowers. One possible explanation for this phenomenon could be the inherent limitations of the random forest, whose final result is obtained by averaging the results of multiple decision trees, which may lead to a decreasing variance of the model's results and an unobtainable prediction value that exceeds the range of observed values [31,62]. Most of the standardized residuals fall into the range −0.5~0.5, signifying good performance of models on most road sections.…”

“…To bridge the research gap, this study aimed to explore the ability of POI to estimate traffic collisions by categories of collisions, types of roads, and periods of the day. In particular, this study introduced the nighttime lights (NTL) dataset [25][26][27][28][29][30][31], a type of remote sensing data, into the crash prediction models. The aim was to explore the ability of the two data sources to map urban road safety, since both of them are easily obtained and are widely acknowledged for reflecting human activities and urban structure.…”

Topology-Aware Road Network Extraction via Multi-Supervised Generative Adversarial Networks

“…On the other hand, learning-based approaches attempt to predict whether a given pixel is a road or not, according to the context around the target pixel [9,10,[36][37][38][39][40]. The extraction is similar to the task of salient objects extraction or segmentation [41][42][43][44][45][46][47].…”

Big Data and Energy Poverty Alleviation

“…Zhao et al [98] used a random forest regression (RFR) model by combining features extracted from multiple data sources, including National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) Day/Night Band (DNB) nighttime light (NTL) data, Google satellite imagery and land cover map, road map and division headquarter location data to estimate poverty based on household wealth index (WI) at a 10-km spatial resolution. The authors trained the RFR model using data in Bangladesh and applied the model to both Bangladesh and Nepal to evaluate the model's accuracy.…”