Nonparametric Conditional Density Estimation In A Deep Learning Framework For Short-Term Forecasting

TL;DR

This paper introduces a flexible nonparametric method for estimating entire conditional distributions in short-term environmental forecasting, demonstrated on tropical cyclone intensity data, enhancing predictive insights beyond point estimates.

Contribution

It proposes a novel approach combining machine learning with a smooth model and logistic transformation to estimate full conditional distributions efficiently.

Findings

Effective in simulation studies across various data distributions.

Demonstrates utility in tropical cyclone intensity forecasting.

Offers a computationally efficient case-control sampling approximation.

Abstract

Short-term forecasting is an important tool in understanding environmental processes. In this paper, we incorporate machine learning algorithms into a conditional distribution estimator for the purposes of forecasting tropical cyclone intensity. Many machine learning techniques give a single-point prediction of the conditional distribution of the target variable, which does not give a full accounting of the prediction variability. Conditional distribution estimation can provide extra insight on predicted response behavior, which could influence decision-making and policy. We propose a technique that simultaneously estimates the entire conditional distribution and flexibly allows for machine learning techniques to be incorporated. A smooth model is fit over both the target variable and covariates, and a logistic transformation is applied on the model output layer to produce an expression of the conditional density function. We provide two examples of machine learning models that can be used, polynomial regression and deep learning models. To achieve computational efficiency we propose a case-control sampling approximation to the conditional distribution. A simulation study for four different data distributions highlights the effectiveness of our method compared to other machine learning-based conditional distribution estimation techniques. We then demonstrate the utility of our approach for forecasting purposes using tropical cyclone data from the Atlantic Seaboard. This paper gives a proof of concept for the promise of our method, further computational developments can fully unlock its insights in more complex forecasting and other applications.