English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A key problem in computational sustainability is to understand thedistribution of species across landscapes over time. This question gives riseto challenging large-scale prediction problems since (i) hundreds of specieshave to be simultaneously modeled and (ii) the survey data are usually inflatedwith zeros due to the absence of species for a large number of sites. Theproblem of tackling both issues simultaneously, which we refer to as thezero-inflated multi-target regression problem, has not been addressed byprevious methods in statistics and machine learning. In this paper, we proposea novel deep model for the zero-inflated multi-target regression problem. Tothis end, we first model the joint distribution of multiple response variablesas a multivariate probit model and then couple the positive outcomes with amultivariate log-normal distribution. By penalizing the difference between thetwo distributions' covariance matrices, a link between both distributions isestablished. The whole model is cast as an end-to-end learning framework and weprovide an efficient learning algorithm for our model that can be fullyimplemented on GPUs. We show that our model outperforms the existingstate-of-the-art baselines on two challenging real-world species distributiondatasets concerning bird and fish populations.

Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation