The importance of monitoring earthquakes for disaster management, public safety, and scientific research can hardly be overstated. The emergence of low-cost seismic sensors offers potential for widespread deployment due to their affordability. Nevertheless, vehicular noise in low-cost seismic sensors presents as a significant challenge in urban environments where such sensors are often deployed. In order to address these challenges, this work proposes the use of an amalgamated deep neural network constituent of a DNN trained on earthquake signals from professional sensory equipment as well as a DNN trained on vehicular signals from low-cost sensors for the purpose of earthquake identification in signals from low-cost sensors contaminated with vehicular noise. To this end, we present low-cost seismic sensory equipment and three discrete datasets that—when the proposed methodology is applied—are shown to significantly outperform a generic stochastic differential model in terms of effectiveness and efficiency.

This study theoretically investigates the role of plant moisture content and its spatial heterogeneity in wildfire dynamics using Cellular Automata models. The model incorporates varying moisture levels and ignition probabilities across different grid configurations, including homogeneous moisture grids and heterogeneous setups with elliptical and segmented high-moisture zones. The relationship between moisture content and ignition probability is modeled using a nonlinear formulation, reflecting threshold-like combustion dynamics observed in real ecosystems. Simulation results show that introducing high-moisture zones significantly reduces the rate of fire spread, with segmented configurations providing the most effective firebreaks. In this context, the ‘suppression effect’ denotes the reductions in forward spread and total burned area attributable to high-moisture regions acting as low-ignitability barriers. The effect is more pronounced when ignition probability depends nonlinearly on moisture, since the nonlinear mapping produces a steeper decline in ignitability above a critical moisture range, which reduces successful transmission across the barrier and increases the likelihood of fire isolation. In particular, the results highlight how modeling can be used as a decision-support tool for the strategic placement of firebreaks. By evaluating alternative spatial configurations of moisture, the approach helps identify barrier designs that maximize containment effectiveness while minimizing ecological and economic costs. This positions the methodology not only as a theoretical contribution but also as a practical framework for guiding firebreak planning and wildfire prevention policies. While the model successfully captures critical fire dynamics, its assumptions of static moisture content and simplified environmental conditions warrant further investigation. Future work will focus on integrating real-time moisture data and refining parameters with observational wildfire data to enhance the model’s predictive capabilities. This study provides valuable insights into the interplay between moisture content and wildfire spread, contributing to the development of decision-support tools for effective wildfire management.