Indoor humidity is a modifiable exposure relevant to respiratory morbidity, mould proliferation, and occupant comfort. Indoor laundry drying is common in energy-constrained homes and can generate multi-hour moisture loads that increase health risk when ventilation is limited. This paper compares humidity dynamics during laundry drying across three conditions in a controlled smart home: a closed non-ventilated room, reactive ventilation activated during drying, and predictive ventilation with scheduled window opening and dehumidifier operation before, during, and after the event. Results show that predictive ventilation suppresses peak humidity, shortens time at elevated levels, accelerates moisture decay, and prevents multi-cycle accumulation; relative to reactive or no ventilation, it maintains lower pre-event humidity and enables faster recovery, reducing cumulative exposure despite similar moisture loads. These empirical patterns support predictive control strategies that act before hazardous exposure rather than relying on post hoc threshold responses, with implications for respiratory symptom monitoring, household behaviour sensing, and scenario-based predictive intervention models in smart homes.

Simulating realistic LiDAR intensity is essential for autonomous driving, particularly under snow conditions, where current methods fail to capture complex LiDAR-to-atmosphere interactions. This paper introduces a CycleGAN framework guided by physics, which incorporates the principles of LiDAR intensity attenuation in snowy weather, significantly narrowing the simulation-to-reality gap. The model was evaluated using an open-source real snow dataset and an open-source simulated dataset, demonstrating its ability to replicate real-world intensity patterns with high accuracy, as indicated by metrics like Structural Similarity Index Measure (SSIM), Kullback-Leibler (KL) Divergence, etc. In the downstream semantic segmentation task, models trained on the enhanced data outperformed those trained on baseline datasets, underscoring the framework's effectiveness in improving LiDAR data realism and robustness in snow-weather autonomous driving scenarios.

LiDAR sensors are integral to autonomous systems, providing a three-dimensional understanding of the surroundings. The intensity of LiDAR returns offers valuable information about the reflected laser signals, which facilitates crucial tasks such as object detection, classification, and segmentation. However, current physics-based LiDAR simulations fail to produce realistic intensity data. This research addresses this issue by using learning-based methods for realistic LiDAR intensity simulation. We propose a hybrid approach that incorporates novel physics-based modalities, specifically incidence angle and material reflectance, into the learning model to generate more realistic intensity data. We test this methodology across two architectures: (i) U-NET (Convolutional Neural Network) and (ii) Pix2Pix (Generative Adversarial Network), using the SemanticKITTI and VoxelScape datasets. The experiments compare the simulated intensity data generated by our method with state-of-the-art approaches through both qualitative and quantitative evaluations, and assessments of its effectiveness in improving the downstream tasks. The results demonstrate consistent improvements after the inclusion of the physics-based modalities.

Sentinel-2 data is highly valuable in remote sensing applications owing to its open accessibility and comprehensive spatial-temporal coverage. However, it poses a unique challenge due to its varying spatial resolutions across its different spectral bands (ranging from 10-m to 60-m). High-resolution data offers finer details and significantly enhances the accuracy of analyses, benefiting a wide range of fields. The majority of current methods for enhancing Sentinel-2 image resolution do not address the enhancement of all bands through a unified network. To address this issue, we propose a novel deep learning-based solution named SenGLEAN, for enhancing multi-resolution bands (specifically, 10-m and 20-m Ground Sampling Distance - GSD) to a unified 5-m GSD. SenGLEAN leverages the concept of Generative LatEnt bANks (GLEAN) and employs a multi-resolution encoder-bank-decoder architecture to achieve high-resolution remote sensing imagery. Notably, our model incorporates channel-attention (CA) and pixel-attention modules (PA) within its design to enhance the spatial quality of results. Through quantitative comparison, we demonstrate that our network shows significant improvements, by increasing the PSNR by 0.28 dB for 10-m bands and 2.92 dB for 20-m bands while reducing the RMSE by 3.11 for 10-m bands and 52.26 for 20-m bands. Furthermore, we introduce a lightweight variant, LightSenGLEAN, retaining critical components while reducing total parameters by 81.89%, which still offers competitive performance. In summary, our proposed model provides an efficient solution to enhance both 10-m and 20-m Sentinel-2 bands to 5-m resolution using a single deep learning framework, facilitating precise image analysis and geoscience applications.

Recently, studies have focused on integrating LiDAR data and satellite images to improve forest canopy height monitoring of large areas. Notably, algorithms based on Random Forest Regression (RFR) and Convolutional Neural Networks (CNN) have shown enhanced accuracy in predicting canopy heights. This study explores the transferability of RFR-based and CNN-based prediction algorithms using airborne LiDAR data and Sentinel-2 images from 2018 and 2021. The 2018 LiDAR and Sentinel-2 were used to train the RFR and CNN prediction algorithms. The trained RFR and CNN algorithms were then used to predict 2018 canopy height from 2018 Sentinel-2 and 2021 canopy height from 2021 Sentinal-2, respectively. Validation results reveal that the RFR-based algorithm achieved a mean absolute error (MAE) of 2.93m for 2018 canopy height and 3.35m for 2021 canopy height. The CNN-based algorithm yielded a MAE of 1.71m for 2018 and 3.78m for 2021. These findings demonstrate the feasibility of predicting forest canopy heights in the same and different years once the RFR and CNN prediction algorithms are properly trained.