Air pollutants pose a significant threat to the environment and human health, thus forecasting accurate pollutant concentrations is essential for pollution warnings and policy-making. Existing studies predominantly focus on single-pollutant forecasting, neglecting the interactions among different pollutants and their diverse spatial responses. To address the practical needs of forecasting multivariate air pollutants, we propose MultiVariate AutoRegressive air pollutants forecasting model (MVAR), which reduces the dependency on long-time-window inputs and boosts the data utilization efficiency. We also design the Multivariate Autoregressive Training Paradigm, enabling MVAR to achieve 120-hour long-term sequential forecasting. Additionally, MVAR develops Meteorological Coupled Spatial Transformer block, enabling the flexible coupling of AI-based meteorological forecasts while learning the interactions among pollutants and their diverse spatial responses. As for the lack of standardized datasets in air pollutants forecasting, we construct a comprehensive dataset covering 6 major pollutants across 75 cities in North China from 2018 to 2023, including ERA5 reanalysis data and FuXi-2.0 forecast data. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods and validate the effectiveness of the proposed architecture.

Reference Evapotranspiration (ET0) is a key parameter for designing smart irrigation scheduling, since it is related by a coefficient to the water needs of a crop. The United Nations Food and Agriculture Organization, proposed a standard method for ET0 computation (FAO56PM), based on the parameterization of the Penman-Monteith equation, that is widely adopted in the literature. To compute ET0 using the FAO56-PM method, four main weather parameters are needed: temperature, humidity, wind, and solar radiation (SR). One way to make daily ET0 estimations for future days is to use freely available weather forecast services (WFSs), where many meteorological parameters are estimated up to the next 15 days. A problem with this method is that currently, SR is not provided as a free forecast parameter on most of those online services or, normally, such forecasts present a financial cost penalty. For this reason, several ET0 estimation models using machine and deep learning were developed and presented in the literature, that use as input features a reduced set of carefully selected weather parameters, that are compatible with common freely available WFSs. However, most studies on this topic have only evaluated model performance using data from weather stations (WSs), without considering the effect of using weather forecast data. In this study, the performance of authors' previous models is evaluated when using weather forecast data from two online WFSs, in the following scenarios: (i) direct ET0 estimation by an ANN model, and (ii) estimate SR by ANN model, and then use that estimation for ET0 computation, using the FAO56-PM method. Employing data collected from two WFSs and a WS located in Vale do Lobo, Portugal, the latter approach achieved the best result, with a coefficient of determination (R2) ranging between 0.893 and 0.667, when considering forecasts up to 15 days.

Recent advancements in numerical simulation methods based on physical models have enhanced the accuracy of weather forecasts. However, the precision diminishes in complex terrains like mountainous regions due to the several kilometers square grid used in numerical simulations. While statistical machine learning has also significantly advanced, its direct application is difficult to utilize physics knowledge. This paper proposes a method that employs machine learning to ``interpolate'' future weather in mountainous regions using current observed data and forecast data from surrounding plains. Generally, weather prediction relies on numerical simulations, so this approach can be considered a hybrid method that indirectly merges numerical simulation and machine learning. The use of binary cross-entropy in precipitation prediction is also examined.

Poor air quality can have a significant impact on human health. The National Oceanic and Atmospheric Administration (NOAA) air quality forecasting guidance is challenged by the increasing presence of extreme air quality events due to extreme weather events such as wild fires and heatwaves. These extreme air quality events further affect human health. Traditional methods used to correct model bias make assumptions about linearity and the underlying distribution. Extreme air quality events tend to occur without a strong signal leading up to the event and this behavior tends to cause existing methods to either under or over compensate for the bias. Deep learning holds promise for air quality forecasting in the presence of extreme air quality events due to its ability to generalize and learn nonlinear problems. However, in the presence of these anomalous air quality events, standard deep network approaches that use a single network for generalizing to future forecasts, may not always provide the best performance even with a full feature-set including geography and meteorology. In this work we describe a method that combines unsupervised learning and a forecast-aware bi-directional LSTM network to perform bias correction for operational air quality forecasting using AirNow station data for ozone and PM2.5 in the continental US. Using an unsupervised clustering method trained on station geographical features such as latitude and longitude, urbanization, and elevation, the learned clusters direct training by partitioning the training data for the LSTM networks. LSTMs are forecast-aware and implemented using a unique way to perform learning forward and backwards in time across forecasting days. When comparing the RMSE of the forecast model to the RMSE of the bias corrected model, the bias corrected model shows significant improvement (27\% lower RMSE for ozone) over the base forecast.

Forecasts by the European Centre for Medium-Range Weather Forecasts (ECMWF; EC for short) can provide a basis for the establishment of maritime-disaster warning systems, but they contain some systematic biases.The fifth-generation EC atmospheric reanalysis (ERA5) data have high accuracy, but are delayed by about 5 days. To overcome this issue, a spatiotemporal deep-learning method could be used for nonlinear mapping between EC and ERA5 data, which would improve the quality of EC wind forecast data in real time. In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model. The study area was the western North Pacific (WNP), and real-time rolling bias corrections were made for 10-day wind-field forecasts released by the EC between December 2020 and November 2021, divided into four seasons. Compared with the original EC forecasts, after correction using the MT-DETrajGRU model the wind speed and wind direction biases in the four seasons were reduced by 8-11% and 9-14%, respectively. In addition, the proposed method modelled the data uniformly under different weather conditions. The correction performance under normal and typhoon conditions was comparable, indicating that the data-driven mode constructed here is robust and generalizable.

Process mining is a family of techniques that support the analysis of operational processes, in terms of key performance indicators, using event data Van Der Aalst (2012). Process mining can be used in number of ways, such as in identifying insights into current processes or in identifying actions or places within workflows where interventions should be made to improve performance. Although processing mining is typically used in the context of commercial business environments, there is crossover to other areas where processes play an important role, such as in water quality management processes administered by local government authorities or citizen science projects that use the Business Process Model and Notation (BPMN) Higgins, Williams, Leibovici, Simonis, Davis, Muldoon, van Genuchten, O'Hare and Wiemann (2016). In the case of water quality management, traditional event log data from information technology systems is often lacking in that many tasks, such as the manual sampling of water and the microbial culturing by biologists and laboratory technicians to identify faecal coliforms, are not performed using computers and are not logged. Nevertheless, it is likely that techniques developed to aid explainability and in the evaluation of machine learning algorithms in such cases will prove using in traditional process mining systems where similar problems must be addressed. This paper focuses on mining suitable features to perform inference for the level of bacteria, and specifically Enterococci and Escherichia coli (E.

Crisis communications have come a long way from call trees and text chains. Today's emergency notification systems and cloud-based notification services are far more effective than relying on employees to call each other. However, these developments have not made crisis communications foolproof. For example, if emergency messages never reach their intended recipients, the sender might not get a notification of the message delivery failure. If a reply message is not generated, an organization's emergency teams could be facing an incident that escalates into a full-blown crisis due to the lack of clear communication.

This paper introduces an improved method of wind power prediction via weather forecast-contextualized Long Short- Term Memory Neural Network (LSTM) models. Wind power and weather forecast data were acquired from open-source databases and combined. However, a generic LSTM model performs poorly on this data, with erratic behavior observed on even low-variance data sections. To address this issue, LSTM modifications were proposed and tested for accuracy through both a Normalized Mean Absolute Error and the Naive Ratio, which is a score introduced by this paper to quantify unwanted "naive" model behavior. Results showed an increase in model accuracy with the addition of weather forecast data to the models, as well as major improvements in performance with some model modifications, which are attributed to the increased contextualization and stability of the new models. These new and improved models have the potential to improve power grid stability and expedite renewable power integration.