Model Ensembles of Artificial Neural Networks and Support Vector Regression for Improved Accuracy in the Prediction of Vegetation Conditions and Droughts in Four Northern Kenya Counties

Abstract

There is increasing need for highly predictive and stable models for the prediction of drought as an aid to better planning for drought response. This paper presents the performance of both homogenous and heterogenous model ensembles in the prediction of drought severity using the study case techniques of artificial neural networks (ANN) and support vector regression (SVR). For each of the homogenous and heterogenous model ensembles, the study investigates the performance of three model ensembling approaches: linear averaging (non-weighted), ranked weighted averaging and model stacking using artificial neural networks. Using the approach of "over-produce then select", the study used 17 years of data on 16 selected variables for predictive drought monitoring to build 244 individual ANN and SVR models from which 111 models were selected for the building of the model ensembles. The results indicate marginal superiority of heterogenous to homogenous model ensembles. Model stacking is shown to realize models that are superior in performance in the prediction of future vegetation conditions as compared to the linear averaging and weighted averaging approaches. The best performance from the heterogenous stacked model ensembles recorded an R 2 of 0.94 in the prediction of future vegetation conditions as compared to an R 2 of 0.83 and R 2 of 0.78 for both ANN and SVR respectively in the traditional champion model approaches to the realization of predictive models. We conclude that despite the computational resource intensiveness of the model ensembling approach to drought prediction, the returns in terms of model performance is worth the investment, especially in the context of the recent exponential increase in computational power.

Gap Filling for Historical Landsat NDVI Time Series by Integrating Climate Data

“…The major component of the CGF method involves using the RBFN model to predict the phenological trajectories of the target year. Machine learning techniques (e.g., artificial neural networks) have been proven to be efficient in predicting vegetation conditions as well as drought events [52]. RBFN used in this paper searches similar patterns in the training set to generate the predicted NDVI time series.…”

Sub-Pixel Convolutional Neural Network for Image Super-Resolution Reconstruction

“…To solve the amplified factor restriction and textural details preservation problems in the mentioned methods, machine learning algorithms are proposed to learn the mapping relationship between the HR and LR images. Support vector regression [9], sparse representation [10], and anchored neighborhood regression (ANR) [11] are popular methods in this category. However, a great number of parameters need to be adjusted manually, and the model is also complex, resulting in weak generalization ability.…”

“…To s amplified factor restriction and textural details preservation problems in the me methods, machine learning algorithms are proposed to learn the mapping relat between the HR and LR images. Support vector regression [9], sparse representat and anchored neighborhood regression (ANR) [11] are popular methods in this c However, a great number of parameters need to be adjusted manually, and the m also complex, resulting in weak generalization ability. Compared with machine learning, deep learning can not only effectively d large amounts of data but also reduces the number of parameters that need to be m adjusted in neural network training, thus remarkably improving the generalizati ity.…”

Assessment of a Spatially and Temporally Consistent MODIS Derived NDVI Product for Application in Index-Based Drought Insurance

“…One example is the MODIS derived Vegetation Condition Index (VCI) used by NDMA, produced by BOKU (University of Natural Resources and Life Sciences, Vienna, Austria) using their NDVI [2]. The product is derived using Aqua and Terra MODIS at the end of each dekad, and in [25,26], it was shown that using machine learning techniques, it is even possible to forecast the VCI one month ahead without significant loss of accuracy. It provides weekly updates of NDVI by applying a Whittaker smoother using available observations within the past 175 days and provides an uncertainty measure at the pixel level [2].…”

“…Furthermore, FEWS NET provides a preliminary estimation of NDVI at near real time and then updates the product after the final smoothing [23]. It is also important to note the effort to forecast NDVI that could aide near real smoothing processes [25][26][27][28], among many others. However, programs like KLIP are dependent on the high accuracy and consistency of the final smoothed eMODIS product.…”