Climate Forecast Research Articles

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

Projecting hydrological response to climate change and urbanization using WEAP model: A case study for the main watersheds of Bicol River Basin, Philippines

Study regionBicol River Basin, Philippines Study focusThe study investigated the impact of climate change and urbanization on water resources in the Philippines. It used Water Evaluation and Planning (WEAP) software and climate forecasts from eight Global Circulation Models (GCMs) to assess the nation's water balance, focusing on two sensitive watersheds: Libmanan-Pulantuna (LPW) and Quinali (QW). The study projects water availability in these areas by creating climate-urbanization scenarios. Furthermore, our endeavor aims to provide insight into the complexities of hydrological processes within traditionally under-observed regions, serving as a blueprint for future environmental planning and sustainable water management in the Philippines and beyond. New hydrological insightsThe study's simulated streamflow matches observed data (R2: 0.70–0.85, NSE: 0.57–0.67) and indicates warming trends and variable precipitation in both watersheds. Rising water demand in domestic and industrial sectors contrasts with a decline in agriculture due to land conversion. QW faces increased water demands from urbanization, while LPW has lower unmet water demand. Low Land Decline scenarios indicate consistent water scarcity in agriculture, while High Land Decline scenarios predict a decrease by 2100. Urbanization significantly impacts future water stress more than climate change, with reduced agricultural land generally associated with lower water stress. Conversely, climate change exacerbates unmet demand issues in domestic and industrial development cases. Due to diminishing agricultural land, both watersheds are expected to transition from water-deficient to water-surplus regions by the end of the century. However, immediate action is crucial to address current water demands, particularly in the severely water-deficient Quinali Watershed.

Dynamical-statistical method for seasonal forecasting of wintertime PM10 concentration in South Korea using multi-model ensemble climate forecasts

Climate conditions and emissions are among the primary influences on seasonal variations in air quality. Consequently, skillful climate forecasts can greatly enhance the predictability of air quality seasonal forecasts. In this study, we propose a dynamical-statistical method for seasonal forecasting of particulate matter (PM10) concentrations in South Korea in winter using climate forecasts from the Asian Pacific Climate Center (APCC) multi-model ensemble (MME). We identified potential climate predictors that potentially affect the wintertime air quality variability in South Korea in the global domain. From these potential climate predictors, those that can be forecasted skillfully by APCC MME were utilized to establish a multiple-linear regression model to predict the winter PM10 concentration in South Korea. As a result of evaluating the forecast skill through retrospective forecasts for the past 25 winters (1995/96-2019/20), this model showed statistically significant forecast skill at a lead time of a month to a season. The skill of PM10 forecast from the MME was overall better than that from a single model. We also found that it is possible to improve forecast skills through optimal MME combinations.

GT-CHES: Graph transformation for classification in human evolutionary systems

While increasingly complex algorithms are being developed for graph classification in highly-structured domains, such as image processing and climate forecasting, they often lead to over-fitting and inefficiency when applied to human interaction networks where the confluence of cooperation, conflict, and evolutionary pressures produces chaotic environments. We propose a graph transformation approach for efficient classification in chaotic human systems that is based on game theoretic, network theoretic, and chaos theoretic principles. Graph structural properties are compiled into time-series that are then transposed into the frequency domain to offer a dynamic view of the system for classification. We propose a set of benchmark data sets and show through experiments that the approach is efficient and appropriate for many dynamic networks in which agents both compete and cooperate, such as social media networks, stock markets, political campaigns, legislation, and geopolitical events.

Nso’ traditional religion and climate forecast: a critical photographic analysis

In light of contemporary ecological challenges affecting our globe, it is increasingly acknowledged that indigenous knowledges are vital for local communities to understand, deal with, and respond to, climate change. Against this background, this article focuses on indigenous religious practices among the Nso’ of the Bamenda Grasslands of Cameroon. The article specifically analyses photographic representations of religious rituals that have shaped, and continue to help, the Nso’ people to accurately forecast climatic conditions and adapt/take precautions. This analysis demonstrates that through photographic narratives the rule of traditional religion in climate forecast can be valorised and exploited to add to the knowledge of climate challenge adaptation. The findings also demonstrate methodologically the role and importance of photographs as a medium for preserving collective and societal memories. (This article is published in the thematic collection ‘African ecologies: literary, cultural and religious perspectives’, edited by Adriaan van Klinken, Simon Manda, Damaris Parsitau and Abel Ugba.)

Impact of Satellite Wind on Improving Simulation of the Upper Ocean Response to Tropical Cyclones

Accurate modeling of the ocean response to tropical cyclones (TCs) requires high-quality wind fields to force ocean models. In this study, blended wind fields are generated using multi-source satellite data and the Climate Forecast System Reanalysis (CFSR) wind data. We utilize the hybrid wind fields to drive the Regional Ocean Modeling System (ROMS) for simulating oceanic dynamic and thermodynamic parameters. The model’s simulated ocean surface and sub-surface temperatures, as well as current speeds, are generally consistent with satellite and in situ observations collected during TC Winston and Freddy. The results are significantly better than those simulated by ROMS using wind forcing from CFSR alone. These results suggest that incorporating satellite wind data into the atmospheric forcing has the potential to enhance vertical mixing and improve simulations of the upper ocean response to TCs.

Financial markets value skillful forecasts of seasonal climate

Scientific agencies spend substantial sums producing and improving forecasts of seasonal climate, but they do so without much information about these forecasts’ value in practice. Here we show that financial market participants value the production of seasonal forecasts: options traders price the uncertainty generated by upcoming United States National Oceanic and Atmospheric Administration Winter and El Niño Outlooks. Each outlook affects firms throughout the economy, with total market capitalization of $6 and $13 trillion, respectively. A 1% improvement in the skill of the El Niño Outlook reduces firms’ exposure to a one standard deviation shock by $18 billion and induces traders to spend an additional $2 million hedging the outlook’s news. Firms must not be able to undertake ex-ante adaptation that would eliminate their exposure to the forecasted portion of seasonal climate without imposing substantial costs of its own.

Comparison of ARIMA boost, Prophet boost, and TSLM models in forecasting Davao City weather data

The geography of the Philippines experiences climate variability thus, providing accurate and timely weather forecasts to the population is crucial. Climate forecasts, which are issued and disseminated by government agencies, serve as essential risk management tools. However, the country faces challenges in forecasting, further exacerbated by climate change. Thus, exploring the use of artificial intelligence has emerged as a strategy to enhance weather prediction accuracy. This research focuses on time series forecasting of rainfall, mean temperature, relative humidity, and wind speed weather data using a machine learning approach. Specifically, it aims to compare and identify the most beneficial forecasting models among autoregressive integrated moving average (ARIMA) boost, Prophet boost, and time series linear model (TSLM). It also seeks to evaluate the performance of these models using mean absolute error (MAE), mean absolute percentage error (MAPE), mean absolute scaled error (MASE), symmetric mean absolute percentage error (SMAPE), root mean squared error (RMSE), and R squared (RSQ) metrics. Results showed that the selection of the forecasting model varies based on the specific parameter under consideration, with no hyperparameter tuning in the analysis. For wind speed, ARIMA boost proves to be a favorable choice. At the same time, TSLM demonstrates effectiveness for relative humidity and mean temperature. Both ARIMA boost and TSLM exhibit strong performance for rainfall. Prophet boost consistently ranks as the least-performing model.

The Hybrid Recharge Delayed Oscillator: A More Realistic El Niño Conceptual Model

Abstract El Niño–Southern Oscillation (ENSO) is the leading mode of climate interannual variability, with large socioeconomical and environmental impacts, potentially increasing with climate change. Improving its understanding may shed further light on its predictability. Here we revisit the two main conceptual models for explaining ENSO cyclic nature, namely, the recharge oscillator (RO) and the advective–reflective delayed oscillator (DO). Some previous studies have argued that these two models capture similar physical processes. Yet, we show here that they actually capture two distinct roles of ocean wave dynamics in ENSO’s temperature tendency equation, using observations, reanalyses, and Climate Model Intercomparison Project (CMIP) models. The slow recharge/discharge process mostly influences central-eastern Pacific by favoring warmer equatorial undercurrent and equatorial upwelling, while the 6-month delayed advective–reflective feedback process dominates in the western-central Pacific. We thus propose a hybrid recharge delayed oscillator (RDO) that combines these two distinct processes into one conceptual model, more realistic than the RO or DO alone. The RDO eigenvalues (frequency and growth rate) are highly sensitive to the relative strengths of the recharge/discharge and delayed negative feedbacks, which have distinct dependencies to mean state. Combining these two feedbacks explains most of ENSO frequency diversity among models. Thanks to the two different spatial patterns involved, the RDO can even capture ENSO spatiotemporal diversity and complexity. We also develop a fully nonlinear and seasonal RDO, even more robust and realistic, investigating each nonlinear term. The great RDO sensitivity may explain the observed and simulated richness in ENSO’s characteristics and predictability. Significance Statement El Niño and La Niña events, and the related Southern Oscillation, cause the largest year-to-year variations of Earth’s climate. Yet the theories behind them are still debated, with two main conceptual models being the recharge oscillator and the delayed oscillator. Our purpose here is to address this debate by developing a more realistic theory, a hybrid recharge delayed oscillator. We show how simple yet realistic it is, with equivalent contributions from the slow recharge process and from the faster delayed feedback. It even captures the observed El Niño and La Niña diversity in space and in frequency. Future studies could use the simple theoretical framework provided here to investigate El Niño–Southern Oscillation (ENSO) in observations, theories, climate models diagnostics and forecasts, and global warming projections.

Spatial and Temporal Variation of Subseasonal-to-Seasonal (S2S) Precipitation Reforecast Skill across the CONUS

Abstract Precipitation forecasts, particularly at subseasonal-to-seasonal (S2S) time scale, are essential for informed and proactive water resource management. Although S2S precipitation forecasts have been evaluated, no systematic decomposition of the skill, Nash–Sutcliffe efficiency (NSE) coefficient, has been analyzed toward understanding the forecast accuracy. We decompose the NSE of S2S precipitation forecast into its three components—correlation, conditional bias, and unconditional bias—by four seasons, three lead times (1–12, 1–22, and 1–32 days), and three models, European Centre of Medium-Range Weather Forecasts (ECMWF), National Centers for Environmental Prediction’s (NCEP) Climate Forecast System (CFS) model, and Environment and Climate Change Canada (ECCC), over the conterminous United States (CONUS). Application of a dry threshold, removal of grid cells with seasonal climatological precipitation means below 0.01 in. per day, is important as the NSE and correlations are lower across all seasons after masking areas with low precipitation values. Further, a west-to-east gradient in S2S forecast skill exists, and forecast skill was better during the winter months and for areas closer to the coast. Overall, ECMWF’s model performance was stronger than both ECCC and NCEP CFS’s performance, mainly for the forecasts issued during the fall and winter months. However, ECCC and NCEP CFS performed better for the forecast issued during the spring months and for areas further from the coast. Postprocessing using simple model output statistics could reduce both unconditional and conditional biases to zero, thereby offering better skill for regimes with high correlation. Our decomposition results show that efforts should focus on improving model parameterization and initialization schemes for climate regimes with low correlation.

Understanding uptake and interrelationship of climatic agricultural innovations in rural Zambia: Evaluating seasonal climate forecast use and weather shocks

Understanding uptake and interrelationship of climatic agricultural innovations in rural Zambia: Evaluating seasonal climate forecast use and weather shocks

Agronomic monsoon onset definitions to support planting decisions for rainfed rice in Bangladesh

The usability gaps between climate information producers and users have always been an issue in climate services. This study aims to tackle the gap for rice farmers in Bangladesh by exploring the potential value of tailored agronomic monsoon onset definitions. Summer aman rice is primarily cultivated under rainfed conditions, and farmers rely largely on monsoon rainfall and its onset for crop establishment. However, farmers’ perception of the arrival of sufficient rains does not necessarily coincide with meteorological definitions of monsoon onset. Therefore, localized agronomic definitions of monsoon onset need to be developed and evaluated to advance in the targeted actionable climate forecast. We analyzed historical daily rainfall from four locations across a north-south gradient in Bangladesh and defined dynamic definitions of monsoon onset based on a set of local parameters. The agronomic onset definition was evaluated in terms of attainable yields simulated by a rice simulation model compared to results obtained using conventional meteorological onset parameters defined by the amount of rainfall received and static onset dates. Our results show that average simulated yields increase up to 7 – 9% and probabilities of getting lower yields are reduced when the year-to-year varying dynamic onset is used over the two drier locations under fully rainfed conditions. It is mainly due to earlier transplanting dates, avoiding the impact of drought experienced with early monsoon demise. However, no yield increases are observed over the two wetter locations. This study shows the potential benefits of generating “localized and translated” climate predictions.

Integration of GSTARIMA Model with Heteroskedastic Error and Kriging for Climate Forecasting: A Systematic Review

Integration of GSTARIMA Model with Heteroskedastic Error and Kriging for Climate Forecasting: A Systematic Review

Farmers Perceptions of Climate Change Issues in Tetritskaro Municipality, Georgia

Agriculture is the traditional and leading field of economy of Tetritskaro Municipality, but faces the challenge of changing climate. The study investigates male and female farmers’ perception of climate change issues in Tetritskaro, their main source of information, adaptation measures choosen and their needs. Climate change data available in Tetritskaro focused on characteristic extreme weather events coupled with face-to-face interviews from 254 farmers (male - 53%, female - 47%) was analyzed. The study revealed that men and women have more or less similar perceptions of climate change issues. For male farmers, the main source of information on climate, seasonal prediction and weather forecast is conversations with fellow farmers, and for female farmers it is indigenous knowledge of the local environment. Male and female farmers, have adapted to the changes in climate similarly applying measures such as pesticides, fertilizer and irrigation, early sowing, and earlier harvest, while the exchange of information between fellow farmers, use of various hail protection products and crop diversification techniques is more frequent among male farmers. Farmers expressed the need for low interest loans to purchase agricultural products, equipment and restore/create windbreak zones. Most of the male farmers indicate the need for introduction new technologies, while female farmers are more in need of information and training in agricultural activities. The study shows the need for development of climate change adaptation policies and interventions in Tetritskaro. Obtained results can be used not only in other agricultural regions of Georgia, but in other countries with the same problems.

Development of Indian summer monsoon precipitation biases in two seasonal forecasting systems and their response to large-scale drivers

Abstract. The Met Office Global Coupled Model (GC) and the National Centers for Environmental Prediction (NCEP) Climate Forecast System (CFSv2) are both widely used for predicting and simulating the Indian summer monsoon (ISM), and previous studies have demonstrated similarities in the biases in both systems at a range of timescales from weather forecasting to climate simulation. In this study, ISM biases are studied in seasonal forecasting setups of the two systems in order to provide insight into how they develop across timescales. Similarities are found in the development of the biases between the two systems, with an initial reduction in precipitation followed by a recovery associated with an increasingly cyclonic wind field to the north-east of India. However, this occurs on longer timescales in CFSv2, with a much stronger recovery followed by a second reduction associated with sea surface temperature (SST) biases so that the bias at longer lead times is of a similar magnitude to that in GC. In GC, the precipitation bias is almost fully developed within a lead time of just 8 d, suggesting that carrying out simulations with short time integrations may be sufficient for obtaining substantial insight into the biases in much longer simulations. The relationship between the precipitation and SST biases in GC seems to be more complex than in CFSv2 and differs between the early part of the monsoon season and the later part of the monsoon season. The relationship of the bias with large-scale drivers is also investigated, using the boreal summer intraseasonal oscillation (BSISO) index as a measure of whether the large-scale dynamics favour increasing, active, decreasing or break monsoon conditions. Both models simulate decreasing conditions the best and increasing conditions the worst, in agreement with previous studies and extending these previous results to include CFSv2 and multiple BSISO cycles.

Distributional effects of the increasing heat incidence on labor productivity

This paper examines how temperature affects worker productivity beyond the usual “on average” analysis, with a particular focus on distributional impacts of the increasing heat incidence across high- and low-productivity areas. Using a recentered influence function regression approach, we estimate unconditional reduced-form effects of a location shift in the temperature distribution—consistent with climate change trends—on the labor productivity distribution across counties in the contiguous U.S. We find that labor productivity is largely insensitive to changes in the frequency of cool-to-moderate maximum daily temperatures. However, as temperatures shift above 24∘C, the effects on productivity turn increasingly negative, albeit with their magnitudes attenuating as a county’s productivity rank rises. While highly productive locations in the top 5% are not adversely impacted even by the hottest temperatures, permanently increasing the incidence of ≥36∘C temperatures just by a day lowers productivity at the bottom vigintile by a nontrivial 0.22% per year, an equivalent of 10.5 hours of work by a minimum-wage worker. As temperatures continue to rise, not only does worker productivity worsen on average, but the cross-county dispersion therein widens too. Given existing climate forecasts, we predict that future extreme temperatures would further deepen worker productivity inequality.

Seasonal climate forecast-an important tool in managing the risk of extreme weather events in Australia's wheat industry

This study aims to investigate the benefits of using the Australian Community Climate and Earth-System Simulator-Seasonal Version 2 (ACCESS-S2), a state-of-the-art seasonal climate forecast (SCF) system, to improve contingent decision-making in the Australian wheat industry. Six locations in eastern Australia, three cultivars with varying maturities, and 17 times of sowing (TOS) were considered. Seasonal hindcasts from ACCESS-S2, initialized on the 1st May for the period 1981–2018 were linked with the Agricultural Production System sIMulator (APSIM)-Wheat model (v7.10) to (1) assess the hindcast skill of ACCESS-S2 in predicting the occurrence of extreme weather events and in predicting above/below long-term median wheat yield; (2) identify optimal management strategies in mitigating the impact of extreme weather events; and (3) quantify the yield benefit of using ACCESS-S2 at the key decision-making point of sowing against a baseline management situation (i.e., without the use of SCF). Research results showed that (1) ACCESS-S2 has varying skills in predicting extreme climate indices and wheat yield across the six locations at a seasonal lead time; (2) 68 % of cases had a yield gain using SCF information; (3) across all cases, there was an average yield gain of 281 kg/ha representing an increase of 13 %; (4) benefits of using SCF were seen across predicted wet years, neutral years and dry years accounting for 69 %, 65 % and 72 % respectively, and (5) the identified optimal management options varied from location to location with earlier sowing associated with either suntop or gregory or both being the optimal strategies at most of the locations considered. Overall, there is a demonstrated benefit in utilizing ACCESS-S2 forecasts in the Australian wheat industry to improve farm management decision-making. The benefit can occur in any climate state but with dry years being more likely and significant (with an average yield increase of 97 % across the locations).

Effectiveness of climate information services: an evaluation of the accuracy and socio-economic benefits for smallholder farmers in Niger and Mali

Climate information services are foundational means of building the farmer’s resilience. However, studies are scarce about the accuracy of climate information services in dryland regions such as the West Africa Sahel, like in Mali and Niger. Thus, this study examined the accuracy of climate forecasts and their socio-economic benefits in these two countries. For rainfall forecasts and alerts, we collected the 2022 data from the ‘SMS Sandji’ platform in Mali (Nara) and the national meteorological agency alert database in Niger (Zinder). The socio-economic benefits of climate information were determined using a sample of 900 individuals in Niger and 227 in Mali. The results indicate that both seasonal and daily climate forecasts have high to moderate accuracy from 0.7 to 0.58 for CSI and 0.11 to 0.43 for BS index in Niger, and 0.94 to 0.91 for CSI, and 0.06 to 0.25 for BS in Mali. The results of field survey show that, in general, 87 to 100% of the respondents in Niger and 100% in Mali received the seasonal forecasts. ANOVA also reveals with high significance (p value = 0.0001) that the utilization of climate information plays a crucial role in improving farmers’ average financial incomes with FCFA 24,943 per hectare at season onset to FCFA 15,355 per hectare during the cropping season, and FCFA 6204 per hectare at the end of the season, and time-saving of 36 h per hectare to 8 h per hectare, depending on the period when the information was used. Globally, this work underscores the importance of climate information services and highlights their positive socio-economic impacts to the livelihood of farmers.

Midsummer precipitation prediction over eastern China by the dynamic downscaling method

AbstractThis study assesses the midsummer precipitation prediction over eastern China by the dynamic downscaling method. Based on the Climate Forecast System version 2 of the National Centers for Environmental Prediction and the Weather Research and Forecasting Model, the prediction performance of global and regional models on the July precipitation over eastern China is further analyzed by hindcast experiments from 1982 to 2010 and prediction experiments from 2011 to 2021. The results suggest that the regional model forced by the global model can noticeably improve the prediction skill for precipitation in eastern China, especially in the region from the South of North China to the Yangtze River Basin, referred as the northern China in this paper. In addition, we perform a diagnostic analysis of the reason for the improvement of the model prediction skill. The results indicate that the high resolution of the regional model and the refinement of physical process parameterizations contribute to improving the simulation ability for the East Asian atmospheric circulation pattern, heat flux, especially for the meridional teleconnection pattern in East Asia and the sensible heat flux in the northern China, thus further improving precipitation prediction.

Remote sensing image information extraction based on Compensated Fuzzy Neural Network and big data analytics

Medical imaging AI systems and big data analytics have attracted much attention from researchers of industry and academia. The application of medical imaging AI systems and big data analytics play an important role in the technology of content based remote sensing (CBRS) development. Environmental data, information, and analysis have been produced promptly using remote sensing (RS). The method for creating a useful digital map from an image data set is called image information extraction. Image information extraction depends on target recognition (shape and color). For low-level image attributes like texture, Classifier-based Retrieval(CR) techniques are ineffective since they categorize the input images and only return images from the determined classes of RS. The issues mentioned earlier cannot be handled by the existing expertise based on a keyword/metadata remote sensing data service model. To get over these restrictions, Fuzzy Class Membership-based Image Extraction (FCMIE), a technology developed for Content-Based Remote Sensing (CBRS), is suggested. The compensation fuzzy neural network (CFNN) is used to calculate the category label and fuzzy category membership of the query image. Use a basic and balanced weighted distance metric. Feature information extraction (FIE) enhances remote sensing image processing and autonomous information retrieval of visual content based on time-frequency meaning, such as color, texture and shape attributes of images. Hierarchical nested structure and cyclic similarity measure produce faster queries when searching. The experiment’s findings indicate that applying the proposed model can have favorable outcomes for assessment measures, including Ratio of Coverage, average means precision, recall, and efficiency retrieval that are attained more effectively than the existing CR model. In the areas of feature tracking, climate forecasting, background noise reduction, and simulating nonlinear functional behaviors, CFNN has a wide range of RS applications. The proposed method CFNN-FCMIE achieves a minimum range of 4–5% for all three feature vectors, sample mean and comparison precision-recall ratio, which gives better results than the existing classifier-based retrieval model. This work provides an important reference for medical imaging artificial intelligence system and big data analysis.