mirror of
https://github.com/zoo-apps/papers.git
synced 2026-11-03 14:59:55 +00:00
zeekayandHanzo Dev
6658236499
Leadership and team cards, board and founding prose, an AI persona modelled on a named individual, contributor and partner entries, and personal correspondence addresses all named one person. The organisation carries them now. Other people keep their names. Where a card, a board list or a founding line named someone else alongside, they stay exactly as they were; only the one entry was removed, and prose that listed two names now reads with one. Sample and fixture data uses the placeholder name these tests already use elsewhere, so the IAM username defect the notes describe still reads as written. The zoo/yapp MIT notice names the foundation that publishes it. Co-authored-by: Hanzo Dev <[email protected]>
116 lines
4.8 KiB
TeX
116 lines
4.8 KiB
TeX
\documentclass[11pt,a4paper]{article}
|
|
\usepackage{shared/zoocover}
|
|
|
|
% ── Packages ──────────────────────────────────────────────────────────────────
|
|
\usepackage[utf8]{inputenc}
|
|
\usepackage[T1]{fontenc}
|
|
\usepackage{lmodern}
|
|
% geometry loaded by zoocover
|
|
\usepackage{amsmath,amssymb,amsfonts}
|
|
\usepackage{graphicx}
|
|
\usepackage{booktabs}
|
|
\usepackage{hyperref}
|
|
\usepackage{cleveref}
|
|
\usepackage{natbib}
|
|
\usepackage{algorithm}
|
|
\usepackage{algorithmic}
|
|
\usepackage{xcolor}
|
|
\usepackage{tikz}
|
|
\usetikzlibrary{arrows.meta,positioning,shapes.geometric}
|
|
\usepackage{float}
|
|
\usepackage{subcaption}
|
|
\usepackage{enumitem}
|
|
\usepackage{microtype}
|
|
\usepackage{fancyhdr}
|
|
\usepackage{abstract}
|
|
|
|
% ── Page Style ────────────────────────────────────────────────────────────────
|
|
\pagestyle{fancy}
|
|
\fancyhf{}
|
|
\fancyhead[L]{\small Zoo Labs Foundation Research}
|
|
\fancyhead[R]{\small Neural Habitat Modeling}
|
|
\fancyfoot[C]{\thepage}
|
|
\renewcommand{\headrulewidth}{0.4pt}
|
|
|
|
% ── Metadata ──────────────────────────────────────────────────────────────────
|
|
\title{%
|
|
\textbf{Neural Habitat Modeling: Predicting Species Distribution\\
|
|
Under Climate Change}\\[0.5em]
|
|
\large Zoo Labs Foundation Paper ZOO-HAB-2026
|
|
}
|
|
|
|
\author{
|
|
Zoo Labs Foundation Research\\
|
|
\texttt{[email protected]}\\[0.5em]
|
|
\small With contributions from the Zoo Open Science Network
|
|
}
|
|
|
|
\date{March 2025}
|
|
|
|
% ── Macros ────────────────────────────────────────────────────────────────────
|
|
\newcommand{\R}{\mathbb{R}}
|
|
\newcommand{\E}{\mathbb{E}}
|
|
\newcommand{\Prob}{\mathbb{P}}
|
|
\newcommand{\Loss}{\mathcal{L}}
|
|
\newcommand{\Dataset}{\mathcal{D}}
|
|
\newcommand{\Species}{\mathcal{S}}
|
|
\newcommand{\Habitat}{\mathcal{H}}
|
|
\newcommand{\Climate}{\mathcal{C}}
|
|
|
|
\begin{document}
|
|
|
|
\zoocoverpage
|
|
|
|
% ── Abstract ──────────────────────────────────────────────────────────────────
|
|
\begin{abstract}
|
|
\noindent
|
|
Predicting how species distributions shift under climate change is among
|
|
the most consequential challenges in conservation biology. Classical
|
|
species distribution models (SDMs) rely on correlative relationships
|
|
between occurrence records and bioclimatic variables, yet they often fail
|
|
to capture complex, non-linear habitat dependencies and spatial
|
|
autocorrelation. We present \textbf{HabitatNet}, a graph neural network
|
|
framework for species distribution modeling that jointly models habitat
|
|
suitability, landscape connectivity, and migration corridors under
|
|
projected climate scenarios. HabitatNet operates on a spatial graph
|
|
representation where nodes encode local environmental features and edges
|
|
capture dispersal potential. We integrate Shared Socioeconomic Pathway
|
|
(SSP) climate projections from CMIP6 to forecast range shifts through
|
|
2100. Evaluated on 847 terrestrial vertebrate species across six
|
|
biogeographic realms, HabitatNet achieves a mean AUC of 0.943 and
|
|
outperforms MaxEnt, random forests, and standard neural SDMs by
|
|
8--14\% on held-out temporal validation sets. The framework identifies
|
|
critical connectivity bottlenecks and proposes optimal corridor
|
|
placements, directly informing conservation prioritization. All models,
|
|
data pipelines, and results are released under open licenses through the
|
|
Zoo Open Science Network.
|
|
|
|
\medskip
|
|
\noindent\textbf{Keywords:} species distribution modeling, graph neural
|
|
networks, climate change, habitat connectivity, migration corridors,
|
|
conservation planning
|
|
\end{abstract}
|
|
|
|
\newpage
|
|
\tableofcontents
|
|
\newpage
|
|
|
|
% ══════════════════════════════════════════════════════════════════════════════
|
|
|
|
\input{sections/01-introduction}
|
|
\input{sections/02-background-and-related-work}
|
|
\input{sections/03-problem-formulation}
|
|
\input{sections/04-habitatnet-architecture}
|
|
\input{sections/05-corridor-identification-algorithm}
|
|
\input{sections/06-data-and-experimental-setup}
|
|
\input{sections/07-results}
|
|
\input{sections/08-case-study-east-african-montane-species}
|
|
\input{sections/09-discussion}
|
|
\input{sections/10-implementation-details}
|
|
\input{sections/11-future-work}
|
|
\input{sections/13-supplementary-feature-importance-analysi}
|
|
\input{sections/14-supplementary-hyperparameter-sensitivity}
|
|
\input{sections/99-conclusion}
|
|
|
|
\end{document}
|