arXiv subjects

Hansani Weeratunge

Publications and source records attributed to Hansani Weeratunge.

6 recordsLinked to original sources

arXiv2026

Bidirectional Multimodal Fusion of Sky Images and Time-Series for Solar Forecasting with Large Language Models

Short-term photovoltaic (PV) power and global horizontal irradiance (GHI) forecasts are essential for effective dispatch, reserve scheduling, and grid operations. At these forecasting horizons, errors are predominantly driven by cloud induced ramps: relying solely on historical numerical data may struggle to anticipate an incoming cloud, making ground-based sky images a crucial complementary physical signal. Furthermore, forecast performance is highly sensitive to location and local observing conditions, creating a strong need for site-specific data that are often scarce. Recently, large language models (LLMs) have demonstrated competitive performance and high data efficiency in time-series forecasting. Despite their success, existing LLM-based forecasting methods remain predominantly unimodal, relying primarily on historical numerical time-series data. Effectively incorporating sky imagery into an LLM-based forecasting framework remains under-explored and an open challenge. In this paper, we propose SolCloudLLM, an LLM-based multimodal forecasting framework. SolCloudLLM aligns sky-image patches with time-series patches and fuses their corresponding representations through bidirectional multimodal fusion, yielding a unified representation that is subsequently mapped into the embedding space of an LLM. Extensive experiments on the SIRTA and SKIPP'D datasets demonstrate that SolCloudLLM consistently outperforms the best baseline methods in MSE across all forecasting horizons, achieving a maximum relative MSE reduction of 25.4%. Stratified analysis further indicates that the benefits of multimodal fusion are concentrated primarily under cloudy conditions. Notably, SolCloudLLM achieves the best performance in nearly all few-shot settings, whereas other deep learning baselines experience substantial performance degradation and are frequently outperformed by the non-learning physical method.

cs.LG↗

arXiv2026

When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making

When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compounds shared errors. Existing collective decision-making methods, including voting, electoral rules, and LLM judges, rely on forward reasoning: they map evidence to labels in one direction. Although these methods can combine diverse forward traces, they still aggregate estimates that share this evidence-to-label factorization and can inherit correlated errors within the forward pool. We therefore construct a reverse posterior for each instance through Bayesian backward reasoning from an explicit likelihood. The forward and reverse posteriors provide differently factorized approximations of the underlying posterior. Because estimates from different factorizations may tend to share the same error less often, we use Jensen-Shannon divergence to rank agents by cross-path consistency. This cross-path consistency signal underlies three strategies: hard selection (MinJS), soft reweighting (FwdJS), and log-linear fusion (LogLin). Evaluated on DDXPlus across five LLM backbones, our proposed strategies show consistent improvements: MinJS outperforms random selection across all backbones, FwdJS generally improves over the strongest baseline, and LogLin achieves the best performance among the evaluated methods, with its largest gains on the subset where the agents disagree. Despite its weaker standalone accuracy, the reverse posterior serves as a more useful anchor than forward-only alternatives, providing complementary information for collective decision-making. When labeled data are available, a lightweight two-stage calibration can further refine the reverse anchor and improve aggregation performance.

cs.AI↗

arXiv2026

Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction

Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (seconds to minutes) caused by cloud movement makes this forecasting task difficult. To address this, using cloud images, which capture the second-to-second changes in cloud cover affecting solar generation, has shown promise. Recently, deep neural networks with attention that focus on important regions of an image have been applied with success in many computer vision applications. However, whether such methods provide meaningful benefits for cloud movement forecasting, and how such improvements propagate through to downstream solar generation forecasting accuracy, remains under-explored. In this study, we conduct a large-scale empirical investigation of the impact of attention-based cloud forecasting on solar generation forecasting, addressing a gap that has been overlooked in the literature. To this end, we develop a pipeline that incorporates an attention-enhanced convolutional long short-term memory network and an existing self-attention-based video prediction method to forecast cloud movement using satellite imagery. The effectiveness of the resulting cloud forecasts is evaluated through their downstream impact on solar forecasting across 50 PV sites in Australia. We further provide insights into the cloud conditions under which attention-based cloud forecasting methods yield the most significant improvements in downstream solar forecasting accuracy. We find that for clouds at high altitudes, the cloud predictions obtained using attention-based methods result in solar forecast skill score improvements of 5.86% or more compared to non-attention-based methods.

cs.LG↗

arXiv2025

Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design

We developed an interpretability informed Bayesian optimization framework to optimize underwater acoustic coatings based on polyurethane elastomers with embedded metamaterial features. A data driven model was employed to analyze the relationship between acoustic performance, specifically sound absorption and the corresponding design variables. By leveraging SHapley Additive exPlanations (SHAP), a machine learning interpretability tool, we identified the key parameters influencing the objective function and gained insights into how these parameters affect sound absorption. The insights derived from the SHAP analysis were subsequently used to automatically refine the bounds of the optimization problem automatically, enabling a more targeted and efficient exploration of the design space. The proposed approach was applied to two polyurethane materials with distinct hardness levels, resulting in improved optimal solutions compared to those obtained without SHAP-informed guidance. Notably, these enhancements were achieved without increasing the number of simulation iterations. Our findings demonstrate the potential of SHAP to streamline optimization processes by uncovering hidden parameter relationships and guiding the search toward promising regions of the design space. This work underscores the effectiveness of combining interpretability techniques with Bayesian optimization for the efficient and cost-effective design of underwater acoustic metamaterials under strict computational constraints and can be generalized towards other materials and engineering optimization problems.

cs.LG↗

arXiv2022

A novel machine learning enabled hybrid optimization framework for efficient and transferable coarse-graining of a model polymer

This work presents a novel framework governing the development of an efficient, accurate, and transferable coarse-grained (CG) model of a polyether material. The proposed framework combines the two fundamentally different classical optimization approaches for the development of coarse-grained model parameters; namely bottom-up and top-down approaches. This is achieved through integrating the optimization algorithms into a machine learning (ML) model, trained using molecular dynamics (MD) simulation data. In the bottom-up approach, bonded interactions of the CG model are optimized using deep neural networks (DNN), where atomistic bonded distributions are matched. The atomistic distributions emulate the local chain structure. In the top-down approach, optimization of nonbonded potentials is accomplished by reproducing the temperature-dependent experimental density. We demonstrate that CG model parameters achieved through our machine-learning enabled hybrid optimization framework fulfills the thermodynamic consistency and transferability issues associated with the classical approaches to coarse-graining model polymers. We demonstrate the efficiency, accuracy, and transferability of the developed CG model, using our novel framework through accurate predictions of chain size as well as chain dynamics, including the limiting behavior of the glass transition temperature, diffusion, and stress relaxation spectrum, where none were included in the potential parameterization process. The accuracy of the predicted properties are evaluated in the context of molecular theories and available experimental data.

physics.chem-ph↗

arXiv2022

A machine learning accelerated inverse design of underwater acoustic polyurethane coatings with cylindrical voids

Here, we report the development of a detailed "Materials Informatics" framework for the design of acoustic coatings for underwater sound attenuation through integrating Machine Learning (ML) and statistical optimization algorithms with a Finite Element Model (FEM). The finite element models were developed to simulate the realistic performance of the acoustic coatings based on polyurethane (PU) elastomers with embedded cylindrical voids. The FEM results revealed that the frequency-dependent viscoelastic behavior of the polyurethane matrix has a significant impact on the magnitude and frequency of the absorption peak associated with the cylinders at low frequencies, which has been commonly ignored in previous studies on similar systems. The data generated from the FEM was used to train a Deep Neural Network (DNN) to accelerate the design process, and subsequently, was integrated with a Genetic Algorithm (GA) to determine the optimal geometric parameters of the cylinders to achieve maximized, broadband, low-frequency waterborne sound attenuation. A significant, broadband, low-frequency attenuation is achieved by optimally configuring the layers of cylindrical voids and using attenuation mechanisms, including Fabry-Pérot resonance and Bragg scattering of the layers of voids. Integration of the machine learning technique into the optimization algorithm further accelerated the exploration of the high dimensional design space for the targeted performance. The developed DNN exhibited significantly increased speed (by a factor of $4.5\times 10^3$ ) in predicting the absorption coefficient compared to the conventional FEM(s). Therefore, the acceleration brought by the materials informatics framework brings a paradigm shift to the design and development of acoustic coatings compared to the conventional trial-and-error practices.

eess.SP↗