Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing

2026-04-30

AI Summary

This work proposes an efficient data valuation method grounded in differentiable AI-based meteorological models to fairly incentivize individual contributions in participatory weather sensing networks. By leveraging gradient attribution to quantify the impact of GFS gridded analysis inputs, the approach introduces gradient signals as a model-driven metric for data value—eliminating the need for a full data assimilation system. The method effectively captures the marginal utility of near-optimal sensor placements and enables monotonic, trustworthy reward allocation. To address potential overvaluation caused by malicious or anomalous data, it further incorporates adversarial input detection and baseline calibration mechanisms, thereby enhancing robustness and reliability in incentive design.

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.

Problem

• data valuation
• reward allocation
• participatory sensing
• weather sensing
• attribution

Innovation

• differentiable AI weather models
• gradient-based attribution
• data valuation
• participatory sensing
• reward allocation