Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing

TL;DR

This paper introduces a gradient-based attribution method using differentiable AI weather models to evaluate data contribution value in participatory weather sensing networks, addressing incentive and valuation challenges.

Contribution

It demonstrates that gradient attribution effectively estimates sensor utility and supports reward allocation, filling a gap in existing data valuation approaches.

Findings

Attribution correlates with sensor placement utility.

Payments based on attribution are monotonically faithful.

Adversarial inputs can inflate attribution scores, requiring external detection.

Abstract

Large-scale IoT weather sensing networks require incentive mechanisms to sustain participation, yet determining how much value individual data contributions bring to the network remains an open problem. Existing approaches address data quality but not data valuation; in operational meteorology, adjoint-based methods derive value from the forecast model itself but require full data assimilation infrastructure. We propose to utilise differentiable AI weather models to fill this gap and characterise gradient-based attribution on gridded GFS analysis inputs as a candidate value signal, evaluating fidelity, calibration, cost, and gaming vulnerability across more than 400 configurations. Attribution captures near-optimal sensor placement utility with monotonically faithful payments, but can be inflated by adversarial inputs, with detection requiring external baseline data. These findings establish gradient attribution as a computationally validated signal for model-informed reward allocation in participatory weather sensing.