Alouette van Hove

• Hove, Alouette van; Aalstad, Kristoffer & Pirk, Norbert (2026). Actively inferring methane sources with drones. Environmental Data Science (EDS). 5. doi: 10.1017/eds.2026.10029. Full text in Research Archive Show summary

  This study presents a framework that combines Bayesian inference with reinforcement learning to guide drone-based sampling for methane source estimation. Synthetic gas concentration and wind observations are generated using a calibrated model derived from real-world drone measurements, providing a more representative testbed that captures atmospheric boundary layer variability. We compare three path planning strategies—preplanned, myopic (short-sighted), and non-myopic (long-term)—and find that non-myopic policies trained via deep reinforcement learning consistently yield more precise and accurate estimates of both source location and emission rate. We further investigate centralized multi-agent collaboration and observe comparable performance to independent agents in the tested single-source scenario. Our results suggest that effective source term estimation depends on correctly identifying the plume and obtaining low-noise concentration measurements within it. Precise localization further requires sampling in close proximity to the source, including slightly upwind. In more complex environments with multiple emission sources, multi-agent systems may offer advantages by enabling individual drones to specialize in tracking distinct plumes. These findings support the development of intelligent, data-driven sampling strategies for drone-based environmental monitoring, with potential applications in climate monitoring, emission inventories, and regulatory compliance.

• Hove, Alouette van; Aalstad, Kristoffer; Lind, Vibeke; Arndt, Claudia; Odongo, Vincent & Ceriani, Rodolfo [Show all 9 contributors for this article] (2025). Inferring methane emissions from African livestock by fusing drone, tower, and satellite data. Biogeosciences. ISSN 1726-4170. 22(16), p. 4163–4186. doi: 10.5194/bg-22-4163-2025. Full text in Research Archive Show summary

  Considerable uncertainties and unknowns remain in the regional mapping of methane sources, especially in the extensive agricultural areas of Africa. To address this issue, we developed an observing system that estimates methane emission rates by assimilating drone and flux tower observations into an atmospheric dispersion model. We used our novel Bayesian inference approach to estimate emissions from various ruminant livestock species in Kenya, including diverse herds of cattle, goats, and sheep, as well as camels, for which methane emission estimates are particularly sparse. Our Bayesian estimates aligned with Tier 2 emission values of the Intergovernmental Panel on Climate Change. In addition, we observed the hypothesized increase in methane emissions after feeding. Our findings suggest that the Bayesian inference method is more robust under non-stationary wind conditions compared to a conventional mass balance approach using drone observations. Furthermore, the Bayesian inference method performed better in quantifying emissions from weaker sources, estimating methane emission rates as low as 100 g h−1. We found a ± 50 % uncertainty in emission rate estimates for these weaker sources, such as sheep and goat herds, which reduced to ± 12 % for stronger sources, like cattle herds emitting 1000–1500 g h−1. Finally, we showed that radiance anomalies identified in hyperspectral satellite data can inform the planning of flight paths for targeted drone missions in areas where source locations are unknown, as these anomalies may serve as indicators of potential methane sources. These promising results demonstrate the efficacy of the Bayesian inference method for source term estimation. Future applications of drone-based Bayesian inference could extend to estimating methane emissions in Africa and other regions from various sources with complex spatiotemporal emission patterns, such as wetlands, landfills, and wastewater disposal sites. The Bayesian observing system could thereby contribute to the improvement of emission inventories and verification of other emission estimation methods.

• Waarum, Ivar-Kristian; Hove, Alouette van; Krogstad, Thomas Røbekk; Ellefsen, Kai Olav & Blomberg, Ann Elisabeth Albright (2025). Mixtures of Gaussian processes for robotic environmental monitoring of emission sources. Environmental Monitoring and Assessment. ISSN 0167-6369. 197(6). doi: 10.1007/s10661-025-14059-6. Full text in Research Archive Show summary

  Emission of greenhouse gases such as methane and carbon dioxide is a known driver of atmospheric heating. Traditional and emerging industries need innovative solutions to comply with increasingly strict sustainability demands and document environmental impact. Mobile sensor platforms such as aerial or underwater vehicles with a high degree of autonomy present a cost-efficient option for environmental monitoring. Autonomous vehicles commonly use Gaussian processes (GPs) for online statistical modelling of concentrations of environmental features. Emission sources in the monitoring area introduce a complication, since the variance is likely heterogeneous between areas dominated by influx and areas with background concentrations. Mixtures of GPs have previously been demonstrated to be effective in such scenarios. Mixture methods distinguish between the natural background concentration and emission to improve model performance when predicting concentrations and variance at unsampled locations. The mixing of GP models allows for nonstationarity and anisotropy in the modelled spatial dynamics, which is desirable for emission modelling in environments with advective forces such as wind or water current. In this paper, we compare different approaches to spatial concentration modelling that accommodate heterogeneous dynamics, based on mixtures of GPs. Distinction of background and emission is either data-driven or derived from domain knowledge. The predictive performance of different mixture methods is demonstrated on field measurements near emissions and compared in an online path planning context. We identify and discuss important trade-offs between data-driven and knowledge-based clustering of measurements. Results show that mixture methods give realistic variance estimates, suitable for online planning.

• Hove, Alouette van; Aalstad, Kristoffer & Pirk, Norbert (2024). Guiding drones by information gain. Proceedings of Machine Learning Research (PMLR). 233(89-96). Full text in Research Archive Show summary

  The accurate estimation of locations and emission rates of gas sources is crucial across various domains, including environmental monitoring and greenhouse gas emission analysis. This study investigates two drone sampling strategies for inferring source term parameters of gas plumes from atmospheric measurements. Both strategies are guided by the goal of maximizing information gain attained from observations at sequential locations. Our research compares the myopic approach of infotaxis to a far-sighted navigation strategy trained through deep reinforcement learning. We demonstrate the superior performance of deep reinforcement learning over infotaxis in environments with non-isotropic gas plumes.

• Hove, Alouette van; Aalstad, Kristoffer & Pirk, Norbert (2023). Using reinforcement learning to improve drone-based inference of greenhouse gas fluxes. Nordic Machine Intelligence (NMI). 3, p. 1–6. doi: 10.5617/nmi.9897. Full text in Research Archive Show summary

  Accurate mapping of greenhouse gas fluxes at the Earth's surface is essential for the validation and calibration of climate models. In this study, we present a framework for surface flux estimation with drones. Our approach uses data assimilation (DA) to infer fluxes from drone-based observations, and reinforcement learning (RL) to optimize the drone's sampling strategy. Herein, we demonstrate that a RL-trained drone can quantify a CO_2 hotspot more accurately than a drone sampling along a predefined flight path that traverses the emission plume. We find that information-based reward functions can match the performance of an error-based reward function that quantifies the difference between the estimated surface flux and the true value. Reward functions based on information gain and information entropy can motivate actions that increase the drone's confidence in its updated belief, without requiring knowledge of the true surface flux. These findings provide valuable insights for further development of the framework for the mapping of more complex surface flux fields.

• Pirk, Norbert; Aalstad, Kristoffer; Westermann, Sebastian; Vatne, Astrid; Hove, Alouette van & Tallaksen, Lena Merete [Show all 8 contributors for this article] (2022). Inferring surface energy fluxes using drone data assimilation in large eddy simulations. Atmospheric Measurement Techniques. ISSN 1867-1381. 15(24), p. 7293–7314. doi: 10.5194/amt-15-7293-2022. Full text in Research Archive Show summary

  Spatially representative estimates of surface energy exchange from field measurements are required for improving and validating Earth system models and satellite remote sensing algorithms. The scarcity of flux measurements can limit understanding of ecohydrological responses to climate warming, especially in remote regions with limited infrastructure. Direct field measurements often apply the eddy covariance method on stationary towers, but recently, drone-based measurements of temperature, humidity, and wind speed have been suggested as a viable alternative to quantify the turbulent fluxes of sensible (H) and latent heat (LE). A data assimilation framework to infer uncertainty-aware surface flux estimates from sparse and noisy drone-based observations is developed and tested using a turbulence-resolving large eddy simulation (LES) as a forward model to connect surface fluxes to drone observations. The proposed framework explicitly represents the sequential collection of drone data, accounts for sensor noise, includes uncertainty in boundary and initial conditions, and jointly estimates the posterior distribution of a multivariate parameter space. Assuming typical flight times and observational errors of light-weight, multi-rotor drone systems, we first evaluate the information gain and performance of different ensemble-based data assimilation schemes in experiments with synthetically generated observations. It is shown that an iterative ensemble smoother outperforms both the non-iterative ensemble smoother and the particle batch smoother in the given problem, yielding well-calibrated posterior uncertainty with continuous ranked probability scores of 12 W m−2 for both H and LE, with standard deviations of 37 W m−2 (H) and 46 W m−2 (LE) for a 12 min vertical step profile by a single drone. Increasing flight times, using observations from multiple drones, and further narrowing the prior distributions of the initial conditions are viable for reducing the posterior spread. Sampling strategies prioritizing space–time exploration without temporal averaging, instead of hovering at fixed locations while averaging, enhance the non-linearities in the forward model and can lead to biased flux results with ensemble-based assimilation schemes. In a set of 18 real-world field experiments at two wetland sites in Norway, drone data assimilation estimates agree with independent eddy covariance estimates, with root mean square error values of 37 W m−2 (H), 52 W m−2 (LE), and 58 W m−2 (H+LE) and correlation coefficients of 0.90 (H), 0.40 (LE), and 0.83 (H+LE). While this comparison uses the simplifying assumptions of flux homogeneity, stationarity, and flat terrain, it is emphasized that the drone data assimilation framework is not confined to these assumptions and can thus readily be extended to more complex cases and other scalar fluxes, such as for trace gases in future studies.

View all works in NVA

• Hove, Alouette van; Aalstad, Kristoffer; Lind, Vibeke; Arndt, Claudia; Odongo, Vincent & Ceriani, Rodolfo [Show all 9 contributors for this article] (2025). Inferring methane emissions from African livestock by fusing drone, tower, and satellite data. 9th International Greenhouse Gas and Animal Agriculture (GGAA2025) conference. Full text in Research Archive
• Aalstad, Kristoffer; Blandini, Giulia; Guidicelli, Matteo; Pirk, Norbert & Hove, Alouette van (2025). Learning to assimilate and assimilating to learn. Full text in Research Archive Show summary

  https://www.hydrologiraadet.no/seminar-om-maskinlaering-innen-hydrologi-og-meteorologi-25-april/

• Hove, Alouette van (2025). Navigating emission plumes. Inferring sources from drone observations via intelligent path planning. Universitetet i Oslo. Full text in Research Archive Show summary

  Drones offer an effective platform for executing targeted flight missions and collecting atmospheric data on greenhouse gas concentrations. These measurements enable the estimation of emission rates from diverse sources. This thesis introduces a modular framework that integrates probabilistic inference and adaptive drone-based sampling to improve the quantification of greenhouse gas emissions, with a focus on methane. By combining Bayesian inversion techniques with reinforcement learning, the proposed approach achieves robust estimation of emission rates and source locations from inherently noisy atmospheric observations. The framework developed by Alouette van Hove was validated through both real-world field campaigns---such as monitoring methane emissions from livestock herds in Kenya---and controlled synthetic experiments. Results demonstrated that Bayesian methods can outperform traditional mass balance techniques, especially for weak emission sources (~100 g CH4 h-1) and under turbulent atmospheric conditions. Furthermore, reinforcement learning agents trained to optimize drone flight paths for maximal information gain consistently surpassed preplanned and myopic strategies in source estimation accuracy. These advances establish a foundation for operational emission monitoring systems capable of supporting climate policy, regulatory compliance, Earth system monitoring, and targeted emission mitigation.

View all works in NVA