Forecast Information Research Articles

Automatic Method for Detecting Deformation Cracks in Landslides Based on Multidimensional Information Fusion

As cracks are a precursor landslide deformation feature, they can provide forecasting information that is useful for the early identification of landslides and determining motion instability characteristics. However, it is difficult to solve the size effect and noise-filtering problems associated with the currently available automatic crack detection methods under complex conditions using single remote sensing data sources. This article uses multidimensional target scene images obtained by UAV photogrammetry as the data source. Firstly, under the premise of fully considering the multidimensional image characteristics of different crack types, this article accomplishes the initial identification of landslide cracks by using six algorithm models with indicators including the roughness, slope, eigenvalue rate of the point cloud and pixel gradient, gray value, and RGB value of the images. Secondly, the initial extraction results are processed through a morphological repair task using three filtering algorithms (calculating the crack orientation, length, and frequency) to address background noise. Finally, this article proposes a multi-dimensional information fusion method, the Bayesian probability of minimum risk methods, to fuse the identification results derived from different models at the decision level. The results show that the six tested algorithm models can be used to effectively extract landslide cracks, providing Area Under the Curve (AUC) values between 0.6 and 0.85. After the repairing and filtering steps, the proposed method removes complex noise and minimizes the loss of real cracks, thus increasing the accuracy of each model by 7.5–55.3%. Multidimensional data fusion methods solve issues associated with the spatial scale effect during crack identification, and the F-score of the fusion model is 0.901.

Demand Information Forecasting and Sharing in a Remanufacturing Closed‐Loop Supply Chain

ABSTRACTWe delve into the incorporation of demand information forecasting and the subsequent information sharing in a closed‐loop supply chain (CLSC). We consider the competition between an original equipment manufacturer (OEM) and an independent remanufacturer (IR). The OEM autonomously determines whether to forecast demand information and further considers whether to disseminate the realized demand signal to the IR. We find that the IR adopts either a partial‐ or a full‐remanufacturing strategy to compete with the OEM. The OEM shares negative demand signals with the IR, as such signals decrease the retail prices and increase the production quantity of all‐new products. Additionally, the sharing of negative demand signals helps alleviate the cannibalization effect caused by the introduction of remanufactured products. When examining the optimal sharing strategy in equilibrium, the OEM only invests in forecasting demand if the forecasting cost is relatively low. Furthermore, the numerical studies reveal that, in equilibrium, the OEM does not necessarily benefit from possessing more precise demand information. Additionally, we assess the influence of consumers' environmental awareness on the production decisions of both companies. The findings indicate that heightened environmental awareness prompts the IR to adopt a full‐remanufacturing strategy, and the information management strategies remain robust.

A Hybrid Spatial Fuzzy Inference and CNN Approach for Forecasting Changes in Remote Sensing

Satellite cloud images, captured by Earth observation satellites, provide crucial information for weather forecasting, aviation, natural resource management, and disaster response. This study presents a novel method for detecting changes in satellite cloud images, combining convolutional neural networks (CNNs) for feature extraction with a spatial complex fuzzy inference system (CFIS). The CNNs effectively capture color channel features in the image blurring and deblurring processes, while the CFIS models the spatiotemporal relationships in the data. Experiments conducted on a US Navy satellite image dataset demonstrate the effectiveness and stability of our proposed method, outperforming related studies in terms of both root mean square error (RMSE) and R-squared (R2) metrics.

Integrating user- and data-driven weather forecasts to develop legitimate, credible, and salient information services for smallholders in the Global South

Climate-related risks and variability pose significant challenges to the livelihoods and food security of smallholder farmers practicing rainfed agriculture. Many smallholders have limited access to weather information from climate services, and this information is often not tailored to their specific context and needs. Therefore, they rely on local ecological knowledge. This study utilizes the second generation of climate services, which provide demand-driven forecast information systems through mobile apps. We present three cases from agricultural communities in Guatemala, Bangladesh, and Ghana where we collaborated with farmers to develop local weather forecasts (LF) and combined them with scientific weather forecasts (SF) to create hybrid weather forecasts (HF). The integration of user-driven forecasts (LF) and data-driven forecasts (SF) enhances the legitimacy of the service, thereby increasing farmers’ trust and credibility by providing skilful forecasts. Furthermore, our results demonstrate that the hybrid weather forecast approach facilitates climate-smart, adaptive agricultural decision-making, enhancing the resilience and capacity of smallholder farmers in the Global South to adapt to a changing climate.

Long-term communication of aftershock forecasts: the Canterbury Earthquake Sequence in Aotearoa, New Zealand

On 14 February 2016, a magnitude (M)5.7 earthquake struck in Christchurch, Aotearoa, New Zealand. The shaking caused damage to historic facades, power outages, cliff collapses, rock falls, liquefaction but no reported injuries or fatalities. This Valentine’s Day earthquake was an aftershock in the Canterbury earthquake sequence (CES), which began on 4 September 2010 with the M7.1 Darfield Earthquake and included the destructive and fatal M6.2 Christchurch aftershock on 22 February 2011. This study eight months after the Valentine’s Day earthquake and six years after the initiation of the CES is the first to explore long-term aftershock forecast information and communication needs. The exploratory study also aimed to gather feedback on aftershock scenarios, an alternate form of communication of the forecast.The qualitative study involved workshops with emergency managers, public health officials, and members of the public in Christchurch. Key findings for long-term communication throughout an earthquake sequence include: 1. divergent earthquake experiences affect aftershock communication response and information needs; 2. understanding aftershock sequence behavior is foundational to sense-making when large aftershocks occur; 3. strategic earthquake sequence updates from the trusted science agency and local agencies could serve as important reminders for earthquake preparedness; 4. communication of aftershock forecast uncertainty could aid with both the credibility of the information and living with uncertainty, and 5. inclusion of impact information and preparedness advice into aftershock forecast scenarios could provide links to actionable information. The paper derives implications for research and practice of long-term communications during an aftershock sequence.

Interpretable Transformer Neural Network Prediction of Diverse Environmental Time Series Using Weather Forecasts

AbstractTransformer neural networks (TNNs) have caused a paradigm shift in deep learning domains like natural language processing, gathering immense interest due to their versatility in other fields such as time series forecasting (TSF). Most current TSF applications of TNNs use only historic observations to predict future events, ignoring information available in weather forecasts to inform better predictions, and with little attention given to the interpretability of the model's use of explanatory inputs. This work explores the potential for TNNs to perform TSF across multiple environmental variables (streamflow, stage, water temperature, and salinity) in two ecologically important regions: the Peace River watershed (Florida) and the northern Gulf of Mexico (Louisiana). The TNN was tested and its prediction uncertainty quantified for each response variable from one‐to fourteen‐day‐ahead forecasts using past observations and spatially distributed weather forecasts. A sensitivity analysis (SA) was performed on the trained TNNs' attention weights to identify the relative influence of each input variable on each response variable across prediction windows. Overall model performance ranged from good to very good (0.78 < NSE < 0.99 for all variables and forecast horizons). Through the SA, we found that the TNN was able to learn the physical patterns behind the data, adapt the use of input variables to each forecast, and increasingly use weather forecast information as prediction windows increased. The TNN's excellent performance and flexibility, along with the intuitive interpretability highlighting the logic behind the models' forecasting decision‐making process, provide evidence for the applicability of this architecture to other TSF variables and locations.

Concurrent droughts across Major River Basins of the World modulated by El Niño–Southern Oscillation

Droughts are among the costliest natural disasters with far-reaching impacts. Focusing on the influence of El Niño–Southern Oscillation (ENSO) on worldwide droughts, this paper presents a formulation of the complex network of concurrent droughts across the Major River Basins (MRBs) of the World. Specifically, concurrent droughts are measured by event synchronization and interconnections of concurrent droughts are determined by significance test. Event coincidence analysis is incorporated into interconnections to quantify the effects of El Niño and La Niña events. A case study is devised for the 3-monthly standardized precipitation index (SPI) of Global Drought and Flood Catalogue during the period from 1950 to 2016. The results highlight that owing to the synchronization of droughts, there exist nine communities of the MRBs, each covering MRBs across different continents. While the correlation between SPI and ENSO exhibits mixed patterns for MRBs grouped by continent, there exist distinct patterns of correlation for MRBs grouped by community. Overall, 28.88% of concurrent droughts tend to be modulated by El Niño events, especially over MRBs in South-West Pacific, South Africa, northern South America and South Asia. In the meantime, 23.51% of concurrent droughts tend to be modulated by La Niña events, especially over MRBs in the United States, southwestern South America, northern China and Central Asia. The modulation of El Niño and La Niña is confirmed by composite analysis of SPI and detailed analysis of the Yangtze River Basin. Overall, the complex network provides useful information for drought forecasting and disaster mitigation.

Unveiling Indian farmers’ adoption of climate information services for informed decision-making: a path to agricultural resilience

ABSTRACT Amidst the intensifying ramifications of climate change on economic conditions, there exists an imperative for farmers to adopt climate forecast information in agricultural decision-making proactively. The research employed an extended theory of planned behaviour to examine the factors influencing farmers’ intentions to incorporate climate information in their decision-making process. Data from 343 male farmers in India were collected using a multi-stage sampling technique and analysed through Partial Least Squares Structural Equation Modelling (PLS-SEM). The results confirm that attitude, subjective norms, perceived behavioural control, perceived benefits and epistemic values significantly and positively affect the farmers’ intention to use climate forecasts in making informed decisions in farming. The findings carry significant importance for advancing adaptation strategies within the agricultural sector, calling for essential measures like fostering the development of farmers’ associations and promoting fruitful collaboration in climate prediction initiatives. Such actions are instrumental in equipping farmers with the necessary tools and knowledge to tackle climate-related challenges and ensure sustainable agricultural practices effectively.

Does analyst forecast informativeness affect managers’ financial reporting incentives?

This study investigates how the informativeness of analyst forecasts affects managers’ financial reporting incentives. Using a novel Match Index to estimate the earnings management induced by analyst forecasts, we find that when analyst forecasts are less informative, managers place less value on using them as a benchmark and thus, engage in less earnings management to meet that benchmark.

A Review of 15 Years of Public Earthquake Forecasting in Aotearoa New Zealand

Abstract New Zealand entered a period of increased seismic activity in 2003, which, to date, has included around 20 large or damaging earthquakes. Building on decades of forecast model research and including research into formal model evaluation, GNS Science, the governmental institution tasked with providing natural hazards information, began issuing public earthquake forecasts following the 2009 Mw 7.2 Darfield earthquake. This article provides a review of the public earthquake forecasting methods and outcomes since that time. Initially the release of forecasts was motivated by the scientific team, but interest, use and understanding quickly rose in the public, government, and private sectors which led to regular refinement and additions to the type of forecast information provided. The basic tenet of forecasting has remained the same, with the forecasts being used to inform decisions requiring consideration of timeframes from days to decades. The operational models were all based on the previous 10–20 years of research in model development and testing; this included the development of methods for combining multiple models into a single hybrid model that typically provides increased statistical forecast skill. The hybrid models combine models from three classes of time horizons: (1) short-term aftershock clustering based on the epidemic-type aftershock sequence class of models, (2) medium-term clustering with time horizons of years to decades, and (3) long-term models with time horizons of decades to nominally time independent. Forecasts have been issued in response to 14 large or significant earthquakes with the forecasts and accompanying information regularly updated on the GeoNet webpages. An important component to the successful deployment and uptake of the models was the foundation laid in the previous decades in model development and testing. This provided understanding and confidence in the models’ ability to provide useful forecasts for response and recovery decisions.

A predictive fuzzy logic and rule-based control approach for practical real-time operation of urban stormwater storage system

Predictive real-time control (RTC) strategies are usually more effective than reactive strategies for the intelligent management of urban stormwater storage systems. However, it remains a challenge to ensure the practicality of RTC strategies that use accessible, non-idealized predictive information while improving their efficiency for successive rainfall events instead of specific phases. This study developed a predictive fuzzy logic and rule-based control (PFL-RBC) approach to address the continuous control of individual storage systems. This approach incorporates total rainfall depth forecast information with an intra-storm fuzzy logic system to optimize peak flow control and several rule-based strategies for pre-storm water detention, reuse, and release control. Computational experiments were conducted using a storage tank case study to test the proposed approach under various rainfall conditions and storage sizes. The results showed that PFL-RBC outperformed static rule-based control in infrequent design storms and realistic continuous rainfall events, reducing flood peaks and volumes by 55 %∼87 % and 7 %∼20 %, respectively, and significantly increasing water detention time and reuse volume. Meanwhile, PFL-RBC required less predictive information to achieve a 6 %∼15 % advantage in peak flow control compared to optimized model predictive control. More importantly, PFL-RBC was reliable in the face of input uncertainty, with <25 % performance loss for water quantity control when the realistic forecast error ranged from -50 % to +50 %. These findings suggest that the proposed approach has great potential to enhance the efficiency and practicality of stormwater storage operations.

Exploration of a model driven by climate to simulate pond water temperature in aquaculture systems

IntroductionInterannual climate variability in the Asian mega deltas has been posing a wide range of climate risks in the aquaculture systems of the region. Water temperature variation is one of the key risks related to disease outbreak, fish health, and loss and damage in fish production. However, Climate information can improve the ability to predict changes in pond water quality parameters at the farm level using publicly available weather and climate data. Little research has been done to translate weather data into water temperature forecasts using mechanistic models in order to provide farmers with relevant forecasting information in the context of climate services.MethodsThe advantage of mechanistic models over statistical models is that they are based on physical processes and can therefore be used in a wider range of environmental conditions. In this study, we used an energy balance model to investigate its ability to simulate pond water temperature at daily and seasonal timescales in the southwest and northeast regions of Bangladesh. The model was able to adequately simulate pond water temperature at a daily timescale using publicly available weather data, and the accuracy of the model was lower at the study site with very heavy rainfall events.ResultsSensitivity analyses showed that the model was also able to simulate the impact of air temperature cold and hot spells on the pond water temperature. Connecting the model with seasonal air temperature forecasts resulted in very small variations in the forecasted seasonal pond water temperature, in large part due to the low variability observed in water temperature at seasonal scale in the study sites.DiscussionClimate information can improve the ability to predict changes in pond water quality parameters at the farm level using publicly available weather and climate data. Hence, these improved predictions are important to help fish-farmers make informed decisions for managing associated climate risks.

Intelligent crude oil price probability forecasting: Deep learning models and industry applications

The crude oil price has been subject to periodic fluctuations because of seasonal changes in industrial demand and supply, weather, natural disasters and global political unrest. An accurate forecast of crude oil prices is of utmost importance for decision makers and industry players in the energy sector. Despite this, the volatility of crude oil prices contributes to the uncertainty of the energy industry, which was particularly challenging following the recent global spread of the COVID-19 epidemic and the Russia–Ukraine conflict. This paper proposes a hybrid deep learning (DL) modelling framework to deal with the volatility of crude oil prices, applying ensemble empirical mode decomposition (EEMD), convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) integrated with quantile regression (QR); named EEMD-CNN-BiLSTM-QR. Two real-world datasets on crude oil prices from the West Texas Intermediate and Brent Crude Oil markets were employed to validate the EEMD-CNN-BiLSTM-QR hybrid modelling framework. Given that the probability density forecast can capture uncertainty, an in-depth analysis was carried out and prediction accuracy calculated. The findings of this study demonstrate that the proposed EEMD-CNN-BiLSTM-QR DL modelling framework, which uses the probability density forecast method, is superior to other tested models in terms of its ability to forecast crude oil prices. The novelty of this study stems mainly from its use of QR, which allows for the description of the conditional distribution of predicted variables and the extraction of more uncertain information for probability density forecasts.

Does Bold Forecast After Job Change Improve Forecast Accuracy? Evidence From Korean Sell‐Side Analysts

AbstractThis paper investigates how incentives generated by intrafirm tournaments affect the informativeness of bold forecasts issued by sell‐side analysts who have recently switched employers. Prior literature suggests that bold forecasts may lose accuracy when they are influenced by tournament‐induced incentives. Extending this literature, I find that bold forecasts from transitioning analysts tend to result in decreased forecast accuracy. This negative effect is mitigated when analysts are less concerned about their disadvantages in the new intrafirm tournament—specifically, when they are more experienced, more competent, or have moved to more prosperous brokerage houses. These findings suggest that bold forecasts by transitioning analysts are partly influenced by intrafirm tournament‐induced risk‐taking, which can deteriorate performance quality.

An Advisor Neural Network framework using LSTM-based Informative Stock Analysis

In the past years, the widespread diffusion of Artificial Intelligence (AI) in the finance domain transformed different services, with particular attention to the stock market. Although different AI-based approaches have been proposed for stock forecasting, they are focused on news content or sentiment without considering fundamental features and vice versa. In turn, other approaches rely on handmade rules or ones based on technical indicators for providing advice without considering contextual information that can strongly affect the stock market. In this paper, we propose an Advisor Neural Network framework using Long Short-Term Memory (LSTM)-based Informative Stock Analysis for Daily investment Advice. Specifically, the forecasting unit relies on a LSTM-based model, which combines technical indicators, contextual information, and financial data for stock forecasting. Successively, the advice unit provides next-day advice based on predicted information in conjunction with the proposed Heuristic Stocks Selection algorithm. This framework has been evaluated on the Stock and Cryptocurrencies markets, considering a subset of 417 stocks and 67 cryptocurrencies over three years, respectively. We compared the proposed framework with several state-of-the-art approaches, showing how it outperforms the baseline in both markets. Furthermore, we achieved a financial gain greater than 41%, despite the downward trend of the NASDAQ market in the quarter under review, and we obtained a 39.38% return on investment for the Cryptocurrencies market.

Point and interval forecasting approach for short-term urban subway passenger flow based on residual term decomposition and fuzzy information granulation

Accurate forecasting information of short-term subway passenger flow is an important scientific reference for daily operations and urban management. The rapid time-varying nature of subway passenger flow caused by various factors that affect travel behavior poses a huge challenge to accurate forecasting. The complexity and uncertainty of data mainly focus on residual terms that deeply reflect the fluctuations. Reasonably mining the residual terms has become the key to achieving accurate forecasting. Therefore, this paper proposes a sophisticated decomposition strategy to extract and analyze the useful information hidden in the residual terms. Firstly, the potential trend, seasonal and residual terms from the original data are extracted by seasonal-trend decomposition procedure based on loess. Secondly, the residual term is decomposed into a series of subcomponents with different frequency features by symplectic geometric mode decomposition. Thirdly, these subcomponents are classified into three clusters based on fuzzy C-means clustering (FCM), and then the corresponding forecasting models are matched to the three obtained clusters and trend and seasonal terms. Finally, based on a decomposition-ensemble framework and information granulation for high-frequency components, we have established point and interval forecasting approach, respectively. Three experiments on real data sets in Beijing, Guangzhou and Shenzhen are conducted to verify the performance of the proposed approach, and the experimental results show that our approach is superior to all benchmark models and contributes to improving operational management and service quality.

Leveraging Collaborative Partnerships to Enhance NWS and Emergency Management Communications through Exercising

Abstract Tabletop exercises examining weather-related hazards are not uncommon but are often built around somewhat generic scenarios that only touch on the meteorological communication environment at a very shallow level. A recent exercise in central Oklahoma sought to change that. A local emergency manager, personnel from a National Weather Service (NWS) forecast office, and a severe weather researcher with a background in exercise design and facilitation worked together to create and deliver a realistic severe weather simulation. Exercise participants were exposed to detailed forecast information via NWSChat—a dedicated communication tool used to connect NWS forecasters, emergency managers, and media members for real-time information sharing. NWS forecasters were able to both actively play in the exercise due to the use of NWSChat and observe how local decision-makers interpreted and utilized the impact-based decision support service (IDSS) graphics and short-term forecast updates. The collaborative approach of developing a detailed scenario with numerous real-world IDSS graphics, along with the use of NWSChat for real-time delivery, resulted in overwhelmingly positive feedback from the participants. The local emergency management office identified numerous areas for improvement in communicating real-time forecast information across their jurisdiction, along with gaps in current plans and resources. Meanwhile, the NWS forecast office had the opportunity to experiment with using the new NWSChat platform in a high-impact severe weather environment before a real-world event took place. Forecasters also gained insight into current IDSS graphic interpretation, noting areas for improved messaging to end users, such as adding storm motion to existing severe weather graphics.

Detectable use of ENSO information on crop production in Southern Africa

People have known that El Niño events are associated with low rainfall in Southern Africa for a century, and seasonal rainfall forecasts are now available in agricultural advisories for farmers. While there is abundant theory as to how farmers might (or should) use seasonal rainfall information on their farms, little is known about whether this information has been widely used or has had widespread benefit. In this study, we use subnational data on cropping area and yield to see if we can detect any macro-level patterns in agricultural choices or outcomes that are related to knowledge of the El Niño Southern Oscillation or seasonal forecast information in Southern Africa. We find that in Lesotho and parts of South Africa, planted area of maize and sorghum is reduced when there is a dry start to the season and an El Niño event is apparent at the time of planting. Similarly, we find that in both Lesotho and most provinces of South Africa, drought years associated with El Niño have worse yields than drought years that are not associated with El Niño (controlling for rainfall). This association could indicate that people are discouraged during El Niño years by the potential for drought, and they might be reducing cropping area, reducing agricultural investments, or turning to other income-generating activities. We are unable to detect a relationship between yields and the accuracy of seasonal rainfall forecasts, therefore we are unable to observe any additional yield benefit when more accurate seasonal forecast information is available.

Green Promotion Service Allocation and Information Sharing Strategy in a Dual-Channel Circumstance

Credit purchase enables the manufacturers in the e-commerce environment to provide pre-sales service that consumers can experience first and pay later. This paper considers demand associated with price and green promotion service level and builds four decentralized game models to study two green promotion service allocation strategies and demand forecasting information sharing strategies in a dual-channel environment. The effects of the degree of dual-channel competition and free-riding on the perfect Bayesian Nash equilibrium are studied. The results show that the retailer should actively cooperate with the manufacturer and share private forecasting information if the coefficient of channel substitution is relatively high. Sharing information will aggravate double marginalization and hurt the retailer. In addition, the retailer’s profit is positively influenced by the forecasting accuracy in four models. When the manufacturer invests in the green promotion service, the prediction accuracy hurts the manufacturer’s profit without information sharing and there is a positive impact with information sharing. In particular, when a retailer provides service, we take the consumer’s free-riding behavior into account, and we find that free-riding hurts both parties and the whole supply chain. In addition, the manufacturer’s profit is irrelevant to the prediction accuracy without information sharing and positively influenced by the accuracy with information sharing.

Convex relaxation of two-stage network-constrained stochastic programming for CHP microgrid optimal scheduling

Different from most studies only incorporating economic aspect into operation scheduling, this paper develops a novel network-constrained framework that can address both economic and secure issues for combined heating and power (CHP) microgrids integrated with wind power considering uncertainties. According to quadratically constrained programs, a two-stage network-constrained stochastic programming (TSNCSP) model is formulated to improve economic benefits and meanwhile capture active/reactive power and off-nominal bus voltage constraints in the full decision variable domain. In the first stage, namely day-ahead, the schedule of transacted electricity with the upstream power grid and the generation cost of heat is determined according to the forecast information. In the second stage, namely real-time, a recourse function of adjustable resources is defined to reduce the expected cost incurred by the perturbation of random wind power outputs. Moreover, the original non-convex problem is innovatively transformed into a semidefinite programming through incorporation of demand response program (DRP), duality, complementary slackness, and relaxation techniques to improve the solving efficiency. Finally, a proposition is presented and proved that provides a sufficient condition for the exactness of the proposed convex relaxation. Numerical simulations on the 33-bus test system verify the effectiveness of the proposed framework in multi-period scenario-based scheduling problems.