HOTA: Hierarchical Overlap-Tiling Aggregation for Large-Area 3D Flood Mapping

Floods are among the most frequent natural hazards and cause significant social and economic damage. Timely, large-scale information on flood extent and depth is essential for disaster response; however, existing products often trade spatial detail for coverage or ignore flood depth altogether. To bridge this gap, this work presents HOTA: Hierarchical Overlap-Tiling Aggregation, a plug-and-play, multi-scale inference strategy. When combined with SegFormer and a dual-constraint depth estimation module, this approach forms a complete 3D flood-mapping pipeline. HOTA applies overlapping tiles of different sizes to multispectral Sentinel-2 images only during inference, enabling the SegFormer model to capture both local features and kilometre-scale inundation without changing the network weights or retraining. The subsequent depth module is based on a digital elevation model (DEM) differencing method, which refines the 2D mask and estimates flood depth by enforcing (i) zero depth along the flood boundary and (ii) near-constant flood volume with respect to the DEM. A case study on the March 2021 Kempsey (Australia) flood shows that HOTA, when coupled with SegFormer, improves IoU from 73\% (U-Net baseline) to 84\%. The resulting 3D surface achieves a mean absolute boundary error of less than 0.5 m. These results demonstrate that HOTA can produce accurate, large-area 3D flood maps suitable for rapid disaster response.

Deep learning approaches to indoor wireless channel estimation for low-power communication

In the rapidly growing development of the Internet of Things (IoT) infrastructure, achieving reliable wireless communication is a challenge. IoT devices operate in diverse environments with common signal interference and fluctuating channel conditions. Accurate channel estimation helps adapt the transmission strategies to current conditions, ensuring reliable communication. Traditional methods, such as Least Squares (LS) and Minimum Mean Squared Error (MMSE) estimation techniques, often struggle to adapt to the diverse and complex environments typical of IoT networks. This research article delves into the potential of Deep Learning (DL) to enhance channel estimation, focusing on the Received Signal Strength Indicator (RSSI) metric - a critical yet challenging aspect due to its susceptibility to noise and environmental factors. This paper presents two Fully Connected Neural Networks (FCNNs)-based Low Power (LP-IoT) channel estimation models, leveraging RSSI for accurate channel estimation in LP-IoT communication. Our Model A exhibits a remarkable 99.02% reduction in Mean Squared Error (MSE), and Model B demonstrates a notable 90.03% MSE reduction compared to the benchmarks set by current studies. Additionally, the comparative studies of our model A with other DL-based techniques show significant efficiency in our estimation models.