Parameter identification for wildfire forecasting models often relies on case-by-case tuning or posterior diagnosis/analysis, which can be computationally expensive due to the complexity of the forward prediction model. In this paper, we introduce an efficient parameter flexible fire prediction algorithm based on machine learning and reduced order modelling techniques. Using a training dataset generated by physics-based fire simulations, the method forecasts burned area at different time steps with a low computational cost. We then address the bottleneck of efficient parameter estimation by developing a novel inverse approach relying on data assimilation techniques (latent assimilation) in the reduced order space. The forward and the inverse modellings are tested on two recent large wildfire events in California. Satellite observations are used to validate the forward prediction approach and identify the model parameters. By combining these forward and inverse approaches, the system manages to integrate real-time observations for parameter adjustment, leading to more accurate future predictions.

The control of droplet formation and size using microfluidic devices is a critical operation for both laboratory and industrial applications, e.g. in micro-dosage. Surfactants can be added to improve the stability and control the size of the droplets by modifying their interfacial properties. In this study, a large-scale data set of droplet size was obtained from high-speed imaging experiments conducted on a flow-focusing microchannel where aqueous surfactant-laden droplets were generated in silicone oil. Three types of surfactants were used including anionic, cationic and non-ionic at concentrations below and above the critical micelle concentration (CMC). To predict the final droplet size as a function of flow rates, surfactant type and concentration of surfactant, two data-driven models were built. Using a Bayesian regularised artificial neural network and XGBoost, these models were initially based on four inputs (flow rates of the two phases, interfacial tension at equilibrium and the normalised surfactant concentration). The mean absolute percentage errors (MAPE) show that data-driven models are more accurate (MAPE = 3.9%) compared to semi-empirical models (MAPE = 11.4%). To overcome experimental difficulties in acquiring accurate interfacial tension values under some conditions, both models were also trained with reduced inputs by removing the interfacial tension. The results show again a very good prediction of the droplet diameter. Finally, over 10 000 synthetic data were generated, based on the initial data set, with a Variational Autoencoder (VAE). The high-fidelity of the extended synthetic data set highlights that this method can be a quick and low-cost alternative to study microdroplet formation in future lab on a chip applications, where experimental data may not be readily available.

Microfluidics is a highly interdisciplinary field where the integration of deep-learning models has the potential to streamline processes and increase precision and reliability. This study investigates the use of deep-learning methods for the accurate detection and measurement of droplet diameters and the image restoration of low-resolution images. This study demonstrates that the Segment Anything Model (SAM) provides superior detection and reduced droplet diameter error measurement compared to the Circular Hough Transform, which is widely implemented and used in microfluidic imaging. SAM droplet detections prove to be more robust to image quality and microfluidic images with low contrast between the fluid phases. In addition, this work proves that a deep-learning super-resolution network MSRN-BAM can be trained on a dataset comprising of droplets in a flow-focusing microchannel to super-resolve images for scales ×2, ×4, ×6, ×8. Super-resolved images obtain comparable detection and segmentation results to those obtained using high-resolution images. Finally, the potential of deep learning in other computer vision tasks, such as denoising for microfluidic imaging, is shown. The results show that a DnCNN model can denoise effectively microfluidic images with additive Gaussian noise up to $\sigma$ = 4. This study highlights the potential of employing deep-learning methods for the analysis of microfluidic images.

Data Assimilation (DA) and Uncertainty quantification (UQ) are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics. Typical applications span from computational fluid dynamics (CFD) to geoscience and climate systems. Recently, much effort has been given in combining DA, UQ and machine learning (ML) techniques. These research efforts seek to address some critical challenges in high-dimensional dynamical systems, including but not limited to dynamical system identification, reduced order surrogate modelling, error covariance specification and model error correction. A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains, resulting in the necessity for a comprehensive guide. This paper provides the first overview of the state-of-the-art researches in this interdisciplinary field, covering a wide range of applications. This review aims at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models, but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems. Therefore, this article has a special focus on how ML methods can overcome the existing limits of DA and UQ, and vice versa. Some exciting perspectives of this rapidly developing research field are also discussed.

Flood prediction is a critical component of disaster preparedness, especially given the substantial economic and social consequences of flooding. As climate change intensifies the frequency and severity of extreme weather events, the need for accurate flood forecasting becomes even more urgent. This study focuses on Bangladesh, applying Convolutional Long-Short Term Memory (ConvLSTM) architectures to predict flooding at a spatial resolution of approximately 2 km, using a straightforward set of publicly available satellite images. The objective is to explore whether machine learning can simplify flood prediction while expanding the coverage of existing models. The model produces pixel-level flood probability maps, showing promising results in predicting large-scale flooding with Area Under the Curve (AUC) values above 0.9 and Structural Similarity Index (SSIM) scores exceeding 0.8. These outputs are both plausible and readily integrable into existing or new disaster response frameworks. As many regions remain underserved by flood prediction systems, this work lays the foundation for scalable machine learning applications that can help mitigate inequalities exacerbated by the increasing risk of flooding.