12 May 2025 in IEEE Access
The spatialization of precipitation data is crucial for studies on climatology, agriculture, and climate change, as well as for urban and environmental planning. Established spatial interpolation methods such as Inverse Distance Weighting are widely used for this purpose. With technological advancements, machine learning techniques have emerged as more efficient and computationally less costly alternatives for performing spatial interpolation calculations. Therefore, this study aims to analyze the performance of machine learning algorithms, including artificial neural networks, comparing them to the Inverse Distance Weighting method. The accuracy of the models was evaluated using the coefficient of determination, root mean square error, and concordance index, to confirm the effectiveness of these methodologies for maximum daily annual precipitation data. After testing different models for data spatialization and conducting a thorough statistical analysis, we conclude that machine learning models outperformed the Inverse Distance Weighting method, yielding greater variability in accumulated Annual Maximum Daily Precipitation values and improved overall results.
28 December 2024 in GEOUSP Espaço e Tempo (Online)
Intense rains are events that can cause significant human and material damage. To mitigate such problems, it is essential that hydraulic structures be analyzed considering the intensity of rains. In this context, heavy rainfall equations analytical expressions obtained from statistical analysis that relate the magnitudes of intensity, duration, and frequency of the largest rains of a given duration are used. This work aimed to determine and spatialize the parameters of heavy rainfall equations for the state of Paraíba, Brazil. Data from rainfall stations provided by the Executive Agency for Water Management of the State of Paraíba were used, along with the computational tools GAM-IDF and QGIS 3.28.10. Additionally, automation algorithms were developed in Python. As a result, parameters were determined for 226 municipalities, and the values were spatialized for locations without data. It is hoped that this work may contribute to studies depending on the intensity of rainfall in Paraiba.