Using satellite images of nighttime lights to predict the economic impact of COVID-19 in India.

The outbreak of COVID-19 in early 2020 heralded a deep global recession not seen since the Second World War. With entire nations in lockdown, burgeoning economies of countries like India plunged into a downward spiral. The conventional instruments of estimating the short-term economic impact of a pandemic is limited, and as a result, it is challenging to implement timely monetary policies to mitigate the financial impact of such unforeseen events. This study investigates the promise of using nighttime images of lights on Earth, also known as nightlight (NTL), captured by the Visible Infrared Imaging Radiometer Suite (VIIRS) instrumentation onboard the Suomi National Polar-Orbiting Partnership (Suomi NPP) satellite mission to measure the economic cost of the pandemic in India. First, a novel data processing framework was developed for a recently released radiance dataset known as VNP46A1, part of NASA's Black Marble suite of NTL products. Second, the elasticity of nightlight to India's National Gross Domestic Product (GDP) was estimated using panel regression followed by machine learning to predict the Year-over-Year (YoY) change in GDP during Fiscal Year (FY) 2020Q1 (Apr-Jun, 2020). Electricity consumption, known to closely track economic output and precipitation were included as additional features to improve model performance. A strong relationship between both electricity usage and nightlight to GDP was observed. The model predicted a YoY contraction of 24% in FY2020Q1, almost identical to the official GDP decline of 23.9% later announced by the Indian Government. Based on the findings, the study concludes that nightlight along with electricity usage can be invaluable proxies for estimating the cost of short-term supply-demand shocks such as COVID-19, and should be explored further.

AI in Healthcare: Time-Series Forecasting Using Statistical, Neural, and Ensemble Architectures.

Both statistical and neural methods have been proposed in the literature to predict healthcare expenditures. However, less attention has been given to comparing predictions from both these methods as well as ensemble approaches in the healthcare domain. The primary objective of this paper was to evaluate different statistical, neural, and ensemble techniques in their ability to predict patients' weekly average expenditures on certain pain medications. Two statistical models, persistence (baseline) and autoregressive integrated moving average (ARIMA), a multilayer perceptron (MLP) model, a long short-term memory (LSTM) model, and an ensemble model combining predictions of the ARIMA, MLP, and LSTM models were calibrated to predict the expenditures on two different pain medications. In the MLP and LSTM models, we compared the influence of shuffling of training data and dropout of certain nodes in MLPs and nodes and recurrent connections in LSTMs in layers during training. Results revealed that the ensemble model outperformed the persistence, ARIMA, MLP, and LSTM models across both pain medications. In general, not shuffling the training data and adding the dropout helped the MLP models and shuffling the training data and not adding the dropout helped the LSTM models across both medications. We highlight the implications of using statistical, neural, and ensemble methods for time-series forecasting of outcomes in the healthcare domain.