The use of remotely sensed rainfall for managing drought risk: a case study of weather index insurance in Zambia

Remotely sensed rainfall is increasingly being used to manage climate-related risk in gauge sparse regions. Applications based on such data must make maximal use of the skill of the methodology in order to avoid doing harm by providing misleading information. This is especially challenging in regions, such as Africa, which lack gauge data for validation. In this study, we show how calibrated ensembles of equally likely rainfall can be used to infer uncertainty in remotely sensed rainfall estimates, and subsequently in assessment of drought. We illustrate the methodology through a case study of weather index insurance (WII) in Zambia. Unlike traditional insurance, which compensates proven agricultural losses, WII pays out in the event that a weather index is breached. As remotely sensed rainfall is used to extend WII schemes to large numbers of farmers, it is crucial to ensure that the indices being insured are skillful representations of local environmental conditions. In our study we drive a land surface model with rainfall ensembles, in order to demonstrate how aggregation of rainfall estimates in space and time results in a clearer link with soil moisture, and hence a truer representation of agricultural drought. Although our study focuses on agricultural insurance, the methodological principles for application design are widely applicable in Africa and elsewhere.

Tensor LRR and sparse coding-based subspace clustering

Subspace clustering groups a set of samples from a union of several linear subspaces into clusters, so that the samples in the same cluster are drawn from the same linear subspace. In the majority of the existing work on subspace clustering, clusters are built based on feature information, while sample correlations in their original spatial structure are simply ignored. Besides, original high-dimensional feature vector contains noisy/redundant information, and the time complexity grows exponentially with the number of dimensions. To address these issues, we propose a tensor low-rank representation (TLRR) and sparse coding-based (TLRRSC) subspace clustering method by simultaneously considering feature information and spatial structures. TLRR seeks the lowest rank representation over original spatial structures along all spatial directions. Sparse coding learns a dictionary along feature spaces, so that each sample can be represented by a few atoms of the learned dictionary. The affinity matrix used for spectral clustering is built from the joint similarities in both spatial and feature spaces. TLRRSC can well capture the global structure and inherent feature information of data, and provide a robust subspace segmentation from corrupted data. Experimental results on both synthetic and real-world data sets show that TLRRSC outperforms several established state-of-the-art methods.

Sparse density estimator with tunable kernels

A new sparse kernel density estimator with tunable kernels is introduced within a forward constrained regression framework whereby the nonnegative and summing-to-unity constraints of the mixing weights can easily be satisfied. Based on the minimum integrated square error criterion, a recursive algorithm is developed to select significant kernels one at time, and the kernel width of the selected kernel is then tuned using the gradient descent algorithm. Numerical examples are employed to demonstrate that the proposed approach is effective in constructing very sparse kernel density estimators with competitive accuracy to existing kernel density estimators.

Sparse density estimation on multinomial manifold combining local component analysis

A new sparse kernel density estimator is introduced based on the minimum integrated square error criterion combining local component analysis for the finite mixture model. We start with a Parzen window estimator which has the Gaussian kernels with a common covariance matrix, the local component analysis is initially applied to find the covariance matrix using expectation maximization algorithm. Since the constraint on the mixing coefficients of a finite mixture model is on the multinomial manifold, we then use the well-known Riemannian trust-region algorithm to find the set of sparse mixing coefficients. The first and second order Riemannian geometry of the multinomial manifold are utilized in the Riemannian trust-region algorithm. Numerical examples are employed to demonstrate that the proposed approach is effective in constructing sparse kernel density estimators with competitive accuracy to existing kernel density estimators.