Site-specific weather forecasts are essential to accurate prediction of power demand and are consequently of great interest to energy operators. However, weather forecasts from current numerical weather prediction (NWP) models lack the fine-scale detail to capture all important characteristics of localised real-world sites. Instead they provide weather information representing a rectangular gridbox (usually kilometres in size). Even after post-processing and bias correction, area-averaged information is usually not optimal for specific sites. Prior work on site optimised forecasts has focused on linear methods, weighted consensus averaging, time-series methods, and others. Recent developments in machine learning (ML) have prompted increasing interest in applying ML as a novel approach towards this problem. In this study, we investigate the feasibility of optimising forecasts at sites by adopting the popular machine learning model gradient boosting decision tree, supported by the Python version of the XGBoost package. Regression trees have been trained with historical NWP and site observations as training data, aimed at predicting temperature and dew point at multiple site locations across Australia. We developed a working ML framework, named 'Multi-SiteBoost' and initial testing results show a significant improvement compared with gridded values from bias-corrected NWP models. The improvement from XGBoost is found to be comparable with non-ML methods reported in literature. With the insights provided by SHapley Additive exPlanations (SHAP), this study also tests various approaches to understand the ML predictions and increase the reliability of the forecasts generated by ML.
An Explainable, Attention-Enhanced, Bidirectional Long Short-Term Memory Neural Network for Joint 48-Hour Forecasting of Temperature, Irradiance, and Relative Humidity
Department of Earth and Atmospheric Sciences, University of Houston（休斯顿大学地球与大气科学系）；Houston Advanced Research Center（休斯顿高级研究中心）
Advancements in numerical weather prediction models have accelerated, fostering a more comprehensive understanding of physical phenomena pertaining to the dynamics of weather and related computing resources. Despite these advancements, these models contain inherent biases due to parameterization and linearization of the differential equations that reduce forecasting accuracy. In this work, we investigate the use of a computationally efficient deep learning method, the Convolutional Neural Network (CNN), as a post-processing technique that improves mesoscale Weather and Research Forecasting (WR…
We introduce NeuralProphet, a successor to Facebook Prophet, which set an industry standard for explainable, scalable, and user-friendly forecasting frameworks. With the proliferation of time series data, explainable forecasting remains a challenging task for business and operational decision making. Hybrid solutions are needed to bridge the gap between interpretable classical methods and scalable deep learning models. We view Prophet as a precursor to such a solution. However, Prophet lacks local context, which is essential for forecasting the near-term future and is challenging to extend due…
Deep learning applied to weather forecasting has started gaining popularity because of the progress achieved by data-driven models. The present paper compares two different deep learning architectures to perform weather prediction on daily data gathered from 18 cities across Europe and spanned over a period of 15 years. We propose the Deep Attention Unistream Multistream (DAUM) networks that investigate different types of input representations (i.e. tensorial unistream vs. multistream ) as well as the incorporation of the attention mechanism. In particular, we show that adding a self-attention…
Ryerson University（瑞尔森大学）；University of Toronto（多伦多大学）；Bogazici University（博阿齐奇大学）
Time series forecasting involves collecting and analyzing past observations to develop a model to extrapolate such observations into the future. Forecasting of future events is important in many fields to support decision making as it contributes to reducing the future uncertainty. We propose explainable boosted linear regression (EBLR) algorithm for time series forecasting, which is an iterative method that starts with a base model, and explains the model's errors through regression trees. At each iteration, the path leading to highest error is added as a new variable to the base model. In th…
Siemens AG（西门子股份公司）；Ludwig Maximilian University of Munich（慕尼黑大学）
Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types. However, information and knowledge evolve continuously, and temporal dynamics emerge, which are expected to influence future situations. In temporal knowledge graphs, time information is integrated into the graph by equipping each edge with a timestamp or a time range. Embedding-based methods have been introduced for link prediction on temporal knowledge graphs, but they mostly lack explainability and comprehensible reasoning chains. Particularly, they are usually not…
SPINEX-TimeSeries: Similarity-based Predictions with Explainable Neighbors Exploration for Time Series and Forecasting Problems
University of Manitoba（曼尼托巴大学）；Clemson University（克莱姆森大学）；Artificial Intelligence Research Institute for Science and Engineering (AIRISE), Clemson University（克莱姆森大学科学与工程人工智能研究院（AIRISE））
MCDFN: Supply Chain Demand Forecasting via an Explainable Multi-Channel Data Fusion Network Model
Khulna University of Engineering and Technology (KUET)（库尔纳工程技术大学）；Okinawa Institute of Science and Technology Graduate University (OIST)（冲绳科学技术大学院大学）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）
Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning
The School of Natural and Computing Sciences and the Interdisciplinary Institute at the University of Aberdeen（阿伯丁大学自然科学与计算科学学院及跨学科研究所）；UiT The Arctic University of Norway（挪威北极大学）
Spatial Temporal Approach for High-Resolution Gridded Wind Forecasting across Southwest Western Australia
International Centre for Radio Astronomy Research, University of Western Australia（国际射电天文研究中心，西澳大利亚大学）；UWA Oceans Institute, University of Western Australia（西澳大利亚大学海洋研究所）
Explainable Earth Surface Forecasting under Extreme Events
Image Processing Laboratory (IPL), Universitat de València（瓦伦西亚大学图像处理实验室）；Remote Sensing Centre for Earth System Research (RSC4Earth), Leipzig University（莱比锡大学地球系统研究遥感中心）；Institute for Earth System Science and Remote Sensing, Leipzig University（莱比锡大学地球系统科学与遥感研究所）；Image and Signal Processing Group, Leipzig University（莱比锡大学图像与信号处理组）；Helmholtz Centre for Environmental Research – UFZ（亥姆霍兹环境研究中心）
StretchCast: Global-Regional AI Weather Forecasting on Stretched Cubed-Sphere Mesh
Institute of Urban Meteorology, China Meteorological Administration (IUM, CMA)（中国气象局城市气象研究所）；LeadSee Team Beijing Meteorological Service（北京气象局LeadSee团队）
Deep learning bears promise for drug discovery, including advanced image analysis, prediction of molecular structure and function, and automated generation of innovative chemical entities with bespoke properties. Despite the growing number of successful prospective applications, the underlying mathematical models often remain elusive to interpretation by the human mind. There is a demand for 'explainable' deep learning methods to address the need for a new narrative of the machine language of the molecular sciences. This review summarizes the most prominent algorithmic concepts of explainable …
In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For this purpose, we establish a data-driven environment by downloading $43$ years of hourly global weather data from the 5th generation of ECMWF reanalysis (ERA5) data and train a few deep neural networks with about $256$ million parameters in total. The spatial resolution of forecast is $0.25^\circ\times0.25^\circ$, comparable to the ECMWF Integrated Forecast Systems (IFS). More importantly, for the first time, an AI-based method outperforms state-of-the-art numerical weather …
A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised learning paradigms like classification and regression, literature on explainability for time series forecasting is relatively scarce. In this paper, we propose a feature-based explainability algorithm, TsSHAP, that can explain the forecast of any black-box forecasting model. The method is agnostic of the forecasting model and can provide explanations f…
Auburn University（奥本大学）；University of Nevada, Reno（内华达大学里诺分校）
In this paper, we analyze the impact of information freshness on supervised learning based forecasting. In these applications, a neural network is trained to predict a time-varying target (e.g., solar power), based on multiple correlated features (e.g., temperature, humidity, and cloud coverage). The features are collected from different data sources and are subject to heterogeneous and time-varying ages. By using an information-theoretic approach, we prove that the minimum training loss is a function of the ages of the features, where the function is not always monotonic. However, if the empi…
Forecasting precipitation in the Arctic using probabilistic machine learning informed by causal climate drivers
Department of Science and Engineering, Sorbonne University, Abu Dhabi, United Arab Emirates（Sorbonne大学科学与工程系）；Physics and Applied Mathematics Unit, Indian Statistical Institute, Kolkata 700108, India（印度统计研究院应用数学与物理单元）；Sorbonne Center for Artificial Intelligence, Sorbonne University, Paris, 75005, France（Sorbonne大学人工智能中心）；Indian Institute of Technology Gandhinagar, Gandhinagar 382355, India（印度理工学院冈丁加尔分校）；National Centre for Polar and Ocean Research, Ministry of Earth Sciences, Vasco da Gama, 403804, India（国家极地与海洋研究中心）；Center for Computational Natural Science and Bioinformatics, International Institute of Information Technology, Gachibowli, Hyderabad-500032, India（国际信息技术研究所计算自然科学与生物信息中心）；Department of Dynamics, Lodz University of Technology, Stefanowskiego 1/15, 90–537 Lodz, Poland（Lodz技术大学动力学系）；Centre for Mathematical Biology and Ecology, Department of Mathematics, Jadavpur University, Kolkata 700032, India（贾瓦德普大学数学生物学与生态中心）
We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19. Our model is explainable by design as it explicitly shows how different compartments evolve and it uses interpretable encoders to incorporate covariates and improve performance. Explainability is valuable to ensure that the model's forecasts are credible to epidemiologists and to instill confidence in end-users such as policy makers and healthcare institutions. Our model can be applied at different geographic resolutions, and here we demonstrate it for states…
Agricultural Recommendation System based on Deep Learning: A Multivariate Weather Forecasting Approach
Chittagong University of Engineering & Technology（吉大港工程技术大学）；Khulna University of Engineering & Technology（库尔纳工程技术大学）；University of Illinois at Chicago（芝加哥大学伊利诺伊分校）；Khulna Agricultural University（库尔纳农业大学）；Edith Cowan University（伊迪丝·考恩大学）
Blue Yonder GmbH（蓝越有限公司）；IU Internationale Hochschule（IU国际大学）；Blue Yonder India Private Limited（蓝越印度私人有限公司）
Demand forecasting is a central component of the replenishment process for retailers, as it provides crucial input for subsequent decision making like ordering processes. In contrast to point estimates, such as the conditional mean of the underlying probability distribution, or confidence intervals, forecasting complete probability density functions allows to investigate the impact on operational metrics, which are important to define the business strategy, over the full range of the expected demand. Whereas metrics evaluating point estimates are widely used, methods for assessing the accuracy…
Enhancing Prediction and Analysis of UK Road Traffic Accident Severity Using AI: Integration of Machine Learning, Econometric Techniques, and Time Series Forecasting in Public Health Research
In this paper we quantify the performances of an automated weather forecast system implemented on the Large Binocular Telescope (LBT) site at Mt. Graham (Arizona) in forecasting the main atmospheric parameters close to the ground. The system employs a mesoscale non-hydrostatic numerical model (Meso-Nh). To validate the model we compare the forecasts of wind speed, wind direction, temperature and relative humidity close to the ground with the respective values measured by instrumentation installed on the telescope dome. The study is performed over a large sample of nights uniformly distributed …
Uncertainty Quantification of Wind Gust Predictions in the Northeast United States: An Evidential Neural Network and Explainable Artificial Intelligence Approach
University of Connecticut（康涅狄格大学）；NSF National Center for Atmospheric Research（NSF国家大气研究中心）
