Tropical Cyclone Damage Assessment using a Projection Pursuit Dynamic Cluster Model

Using data from 62 tropical cyclones (TCs) that landed in Guangdong Province in China between 2000 and 2019, we calculated six indices—minimum central pressure, maximum wind speed, maximum rainstorm ratio, cumulative surface rainfall, cyclone track length and lifetime—and constructed a projection pursuit dynamic cluster (PPDC) model to assess TC damage risk. Although a single index may provide correct information on the intensity of certain types of damage, a comprehensive damage risk assessment cannot be obtained from individual indices alone. The PPDC model is a stable tool for TC damage risk assessment, especially in terms of economic loss, agricultural disaster area and disaster-affected population. Model validation improved the correlation of each of the indices. Output from the PPDC model for disaster-affected population and agricultural disaster-affected area also improved after model validation. We examined the limitations of the single indices using data from three TCs. Output from the PPDC model can closely reflect the intensity of the damage caused by the cyclones. Projection pursuit dynamic clustering is a new and objective method for typhoon damage risk assessment, and provides the scientific basis to support disaster prevention and mitigation.

How deep is your model? Network topology selection from a model validation perspective

Deep learning is a powerful tool, which is becoming increasingly popular in financial modeling. However, model validation requirements such as SR 11-7 pose a significant obstacle to the deployment of neural networks in a bank’s production system. Their typically high number of (hyper-)parameters poses a particular challenge to model selection, benchmarking and documentation. We present a simple grid based method together with an open source implementation and show how this pragmatically satisfies model validation requirements. We illustrate the method by learning the option pricing formula in the Black–Scholes and the Heston model.

Construction of a prediction model for drug removal rate in hemodialysis based on chemical structures

In designing drug dosing for hemodialysis patients, the removal rate (RR) of the drug by hemodialysis is important. However, acquiring the RR is difficult, and there is a need for an estimation method that can be used in clinical settings. In this study, the RR predictive model was constructed using the RR of known drugs by quantitative structure–activity relationship (QSAR) analysis. Drugs were divided into a model construction drug set (75%) and a model validation drug set (25%). The RR was collected from 143 medicines. The objective variable (RR) and chemical structural characteristics (descriptors) of the drug (explanatory variable) were used to construct a prediction model using partial least squares (PLS) regression and artificial neural network (ANN) analyses. The determination coefficients in the PLS and ANN methods were 0.586 and 0.721 for the model validation drug set, respectively. QSAR analysis successfully constructed dialysis RR prediction models that were comparable or superior to those using pharmacokinetic parameters. Considering that the RR dataset contains potential errors, we believe that this study has achieved the most reliable RR prediction accuracy currently available. These predictive RR models can be achieved using only the chemical structure of the drug. This model is expected to be applied at the time of hemodialysis. Graphic Abstract