Objective and probabilistic long-range forecasts of summertime air temperatures in South Korea based on Gaussian processes

We propose the objective long-range forecasting model based on Gaussian processes (OLRAF-GP), focusing on summertime near-surface air temperatures in June (1-month lead), July (2-month lead), and August (3-month lead). The predictors were objectively selected based on their relationships with the target variables, either from observations (GP-OBS) or from observations and dynamical climate model results from APEC Climate Center multi-model ensemble (APCC MME) for the period with no observed data (GP-MME). The performances of the OLRAF-GP models were compared with the model with pre-determined predictors from observations (GP-PD). Both GP-MME and GP-OBS outperformed GP-PD in June (Heidke skill score; HSS = 0.46, 0.72, and 0.16 for mean temperature) and July (HSS = 0.53, 0.3, and 0.07 for mean temperature). Furthermore, GP-MME mostly outperformed GP-OBS and GP-PD in August (HSS = 0.52, 0.28, and 0.5, respectively, for mean temperature), implying larger contributions of the additional predictors from MME. OLRAF-GP models, especially GP-MME, are expected to better forecast summertime temperatures in regions where existing models have been struggling. We find that the physical processes associated with the notable predictors are aligned with those in previous studies, such as the attribution of the La Niña conditions in the previous winter, the related Indian Ocean capacitor effect, and the impacts of wintertime Polar/Eurasia pattern. These results imply that the mechanisms of the objectively selected predictors can be physically meaningful, and their inclusion can improve model performance and efficiency.

Public Health Policy Pillars for the Sustainable Elimination of Zoonotic Schistosomiasis

Schistosomiasis is a parasitic disease acquired through contact with contaminated freshwater. The definitive hosts are terrestrial mammals, including humans, with some Schistosoma species crossing the animal-human boundary through zoonotic transmission. An estimated 12 million people live at risk of zoonotic schistosomiasis caused by Schistosoma japonicum and Schistosoma mekongi, largely in the World Health Organization’s Western Pacific Region and in Indonesia. Mathematical models have played a vital role in our understanding of the biology, transmission, and impact of intervention strategies, however, these have mostly focused on non-zoonotic Schistosoma species. Whilst these non-zoonotic-based models capture some aspects of zoonotic schistosomiasis transmission dynamics, the commonly-used frameworks are yet to adequately capture the complex epi-ecology of multi-host zoonotic transmission. However, overcoming these knowledge gaps goes beyond transmission dynamics modelling. To improve model utility and enhance zoonotic schistosomiasis control programmes, we highlight three pillars that we believe are vital to sustainable interventions at the implementation (community) and policy-level, and discuss the pillars in the context of a One-Health approach, recognising the interconnection between humans, animals and their shared environment. These pillars are: (1) human and animal epi-ecological understanding; (2) economic considerations (such as treatment costs and animal losses); and (3) sociological understanding, including inter- and intra-human and animal interactions.

Finite deformation and fractional order viscoelasticity of an auxetic foam

Auxetic foams exhibit novel mechanical properties due to their unique microstructure for improved energy-absorption and cavity expansion applications that have fascinated the scientific community since their inception. Given the advancements in material processing and performance of polymer open cell auxetic foams, there is a strong desire to fully understand the nonlinear rate-dependent deformation of these materials. The influence of nonlinear compressibility is introduced here along with relaxation effects to improve model predictions for different stretch rates and finite deformation regimes. The viscoelastic behavior of the material is analyzed by comparing fractional order and integer order calculus models. All results are statistically validated using maximum entropy methods to obtain Bayesian posterior densities for the hyperelastic, auxetic, and viscoelastic parameters. It is shown that fractional order viscoelasticity provides [Formula: see text]–[Formula: see text] improvement in prediction over integer order viscoelastic models when the model is calibrated at higher stretch rates where viscoelasticity is more significant.

Optimization of Process Conditions for Effective Degradation of Azo Blue Dye by Streptomyces sp. DJP15: A Secondary Modelling Approac

The well function of aquatic and soil organisms including terrestrial, as well as those of all other living things, can be jeopardized if dyes aren't properly treated, as their degradation might lead to carcinogenic chemicals. Complete mineralization of dye is the only option, and this can be done using microorganisms. The azo blue dye inhibitory effect to its biodegradation by Streptomyces DJP15 was modelled using several inhibition kinetic models such as Haldane, Monod, Luong, Aiba, Teissier-Edwards, Han-Levenspiel and Yano. The result shows that only the Luong model failed to fit the data. The rest of the models visually ft the data although data fitting is problematic with datapoints of less than 10, which the result in this work demonstrates where it is not easy to choose the best model where nearly all of the models fit the data in a similar manner. Resorting to statistical discriminatory function, the best model was Monod with the smallest RMSE and AICc values and the highest adjR2 values and values for AF and BF close to unity. However, Monod has only two parameters and is the most robust. The Monod’s parameters were maximum specific degradation rate of 0.431 (1/h) (95% confidence interval from 0.391 to 0.456) and concentration of substrate giving half maximal rate or Ks value of 0.0001 (mg/L) (95% C.I. from -0.01 to 12.12). The confidence interval value for the Ks value was very large indicating poor data quality. This should be an important consideration in future works where the data point number can be increased to improve model fitting exercise.

Improving Accuracy of Tomato Plant Disease Diagnosis Based on Deep Learning With Explicit Control of Hidden Classes

Recognizing plant diseases is a major challenge in agriculture, and recent works based on deep learning have shown high efficiency in addressing problems directly related to this area. Nonetheless, weak performance has been observed when a model trained on a particular dataset is evaluated in new greenhouse environments. Therefore, in this work, we take a step towards these issues and present a strategy to improve model accuracy by applying techniques that can help refine the model’s generalization capability to deal with complex changes in new greenhouse environments. We propose a paradigm called “control to target classes.” The core of our approach is to train and validate a deep learning-based detector using target and control classes on images collected in various greenhouses. Then, we apply the generated features for testing the inference of the system on data from new greenhouse conditions where the goal is to detect target classes exclusively. Therefore, by having explicit control over inter- and intra-class variations, our model can distinguish data variations that make the system more robust when applied to new scenarios. Experiments demonstrate the effectiveness and efficiency of the proposed approach on our extended tomato plant diseases dataset with 14 classes, from which 5 are target classes and the rest are control classes. Our detector achieves a recognition rate of target classes of 93.37% mean average precision on the inference dataset. Finally, we believe that our study offers valuable guidelines for researchers working in plant disease recognition with complex input data.

Federated Learning with Random Communication and Dynamic Aggregation

Federated Learning (FL) is a setting that allows clients to train a joint global model collaboratively while keeping data locally. Due to FL has advantages of data confidential and distributed computing, interest in this area has increased. In this paper, we designed a new FL algorithm named FedRAD. Random communication and dynamic aggregation methods are proposed for FedRAD. Random communication method enables FL system use the combination of fixed communication interval and constrained variable intervals in a single task. Dynamic aggregation method reforms aggregation weights and makes weights update automately. Both methods aim to improve model performance. We evaluated two proposed methods respectively, and compared FedRAD with three algorithms on three hyperparameters. Results at CIFAR-10 demonstrate that each method has good performance, and FedRAD can achieve higher classification accuracy than state-of-the-art FL algorithms.