Organizations: CMCC Foundation – Euro-Mediterranean Center on Climate Change, Venice, Italy · Department of Environmental Sciences, Informatics and Statistics, Ca’ Foscari University of Venice, Italy · Griffith University, Gold Coast, Australia · Apter, Byron Bay, Australia · European Centre for Living Technology, Venice, Italy
When a storm surge approaches a coastal town, the emergency plan must be put into action quickly using water-level forecasts, flood extent, road access, vulnerable residents and shelters. Bringing this information together under time pressure is slow and depends on the duty officer's expertise. This paper is one step in a wider research line from data to safe decisions: machine learning to understand the hazard, reinforcement learning and planning to choose actions, large language models (LLMs) to explain and cross-check them, and an assurance layer that keeps people in charge. Here we address the action step on a real place. We ask whether a policy can learn the timing of emergency actions from decades of real events. Lido di Venezia is represented as a heterogeneous graph built from public elevation, road, building and census data and driven by hourly tide-gauge records from 1983 to 2024, with seven actions taken from the municipal emergency plan. A PPO policy is trained on this graph and compared, on storm windows unseen in training, with a rule-based system simulating the officer's discretionary decisions. On 18 historical test scenarios, PPO achieves a similar reduction in population exposure to the rule. With uncertain forecasts and limited protection it again performs similarly but does not outperform the tuned rule, and removing graph message passing does not substantially reduce performance. PPO therefore learns an effective protective response from an outcome-based reward alone: it is given the plan's actions and when each is allowed, but not the thresholds that tell the comparator when to act. Next steps test harder edge cases, move closer to a digital twin of the territory, and replace the simulated officer with assessment by emergency-management stakeholders, supported by LLM-based interpretation of each recommendation.
Figures & tables
Figure 1: The environment and the two deciders, connected by state, actions and reward.
Action
Plan §
Type
Preconditions
Effect
Lat.
Cost
monitor
4.1.4.1, 4.1.5.5
default
always legal (no-op)
—
0
0
issue_alert
4.1.4.9
mandate
1-h forecast ≥110 cm; not yet alerted
preparedness flag
0
0
deploy_sandbags
4.1.4.8
discr.
exposed zone; resources ≥1
+40 cm protection
1
1
close_road
4.1.4.9
discr.
junction water level ≥ flood threshold
junction blocked
0
0
open_shelter
5.3.2, 4.1.4.8
discr.
accessible; capacity >0 ; not active; resources ≥1
shelter active
1
1
assisted_evacuation
4.2.3.1, 4.2.3.4
discr.
zone not evacuated; passable path to a shelter; resources ≥1
zone evacuated
1
1
Table 1: The seven plan-derived actions [ 1 ] : type, legality preconditions, effect, latency (h) and cost (budget 5).
Policy
Exposure (person-h) ↓
Displacement (person-h) ↓
Peak exposed (persons)
Zero-exposure windows
Mandates only (literal plan)
2,424
40,920
805
0.39
Plan-extended
1,439
47,269
722
0.39
Static trigger (tune-selected)
308
41,721
233
0.72
No message passing
285 ± 77
42,007
210
0.74
Learned policy
262 ± 26
42,007
187
0.77
Table 2: Test 1 ladder, 18 test windows (per-window means; learned rows mean ± std, 5 seeds).
During disasters, cascading failures across power grids, communication networks, and social behavior amplify community fear and undermine cooperation. Existing cyber-physical-social (CPS) models simulate these coupled dynamics but lack mechanisms for active intervention. We extend the CPS resilience model of Valinejad and Mili (2023) with control channels for three agencies, communication, power, and emergency management, and formulate the resulting system as a three-player non-zero-sum differential game solved via online actor-critic reinforcement learning. Simulations based on Hurricane Harvey data show 70% mean fear reduction with improved infrastructure recovery; cross-validation in the case of Hurricane Irma (without refitting) achieves 50% fear reduction, confirming generalizability.
Yashodhan D. Hakke, Almuatazbellah M. Boker, Lamine Mili +2
Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA · Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA · Department of Computer Science, Virginia Tech, Blacksburg, VA, USA
Estimating extreme risk in reinforcement learning becomes increasingly difficult as the confidence level increases, since only a small number of observations contribute to empirical estimates of Conditional Value-at-Risk (CVaR). In this paper, we extend an Extreme Value Theory (EVT) approach for CVaR optimization to high-dimensional neural-network policies. Using a peaks-over-threshold representation and method-of-moments estimation, we obtain a differentiable tail-risk objective and show that, conditional on the selected threshold, its finite-sample gradient can be computed directly through automatic differentiation. We first validate the approach in a controlled experiment with a known optimal solution and then investigate its performance in a deep-hedging problem with rare extreme market movements. Our results show similar hedging behavior for EVT- and empirical-CVaR-trained policies under normal conditions, while EVT-trained policies exhibit lower hedging losses under the extreme-scenario evaluation across the training sample sizes considered. These results suggest that EVT can provide a practical alternative for training neural policies when the observations relevant to extreme risk are scarce.
Carlos Octavio Pérez Mendoza, Frédéric Godin
Concordia University, Department of Mathematics and Statistics, Montréal, Canada · Quantact Laboratory, Centre de Recherches Mathématiques, Montréal, Canada
Accurate and efficient storm-surge emulation is essential for coastal hazard assessment, yet high-fidelity hydrodynamic models remain too expensive for large scenario ensembles and rapid evaluation under heterogeneous climate forcings. We present PACT, a peak-aware cross-attention graph transformer for efficient station-level storm-surge prediction from atmospheric forcing fields. PACT represents each forcing patch as a graph, encodes spatial structure with GraphSAGE, and uses a learned station query to aggregate node information through cross-attention rather than uniform pooling. A Transformer encoder models temporal dependence across the forcing history, and a horizon-query decoder generates lead-specific forecasts from a shared temporal memory. To better capture extreme events, we introduce a peak-aware learning strategy that couples a lightweight auxiliary peak-aware head with a tailored training objective, including a tail-focused loss on peak-dominated samples and a horizon-wise slope regularizer to encourage coherent multi-step evolution. Across multiple tide-gauge stations along the US Northeast coast, PACT outperforms a strong spatio-temporal graph neural network baseline in both RMSE and MAE. Diagnostics show improved peak fidelity and tail preservation for reanalysis and most CMIP6 datasets. PACT is also computationally efficient, requiring about 3.5~s to generate a full winter-season surge trajectory for one year after training. Under distribution shift across five CMIP6 forcings, PACT transfers well within the CMIP6 family but degrades markedly when transferring from reanalysis to climate-model forcings, highlighting a persistent reanalysis--GCM gap.
Zesheng Liu, Doyup Kwon, Ning Lin +1
Department of Computer Science and Engineering, Lehigh University · Department of Civil and Environmental Engineering, Princeton University · Department of Civil and Environmental Engineering, Lehigh University