Hasil untuk "Meteorology. Climatology"

Sourish Das, Sudeep Shukla, Abbinav Sankar Kailasam et al.

Agricultural price volatility challenges sustainable finance, planning, and policy, driven by market dynamics and meteorological factors such as temperature and precipitation. In India, the Minimum Support Price (MSP) system acts as implicit crop insurance, shielding farmers from price drops without premium payments. We analyze the impact of climate on price volatility for soybean (Madhya Pradesh), rice (Assam), and cotton (Gujarat). Using ERA5-Land reanalysis data from the Copernicus Climate Change Service, we analyze historical climate patterns and evaluate two scenarios: SSP2.4.5 (moderate case) and SSP5.8.5 (severe case). Our findings show that weather conditions strongly influence price fluctuations and that integrating meteorological data into volatility models enhances risk-hedging. Using the Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) model, we estimate conditional price volatility and identify cross-correlations between weather and price volatility movements. Recognizing MSP's equivalence to a European put option, we apply the Black-Scholes model to estimate its implicit premium, quantifying its fiscal cost. We propose this novel market-based risk-hedging mechanism wherein the government purchases insurance equivalent to MSP, leveraging Black-Scholes for accurate premium estimation. Our results underscore the importance of meteorological data in agricultural risk modeling, supporting targeted insurance and strengthening resilience in agricultural finance. This climate-informed financial framework enhances risk-sharing, stabilizes prices, and informs sustainable agricultural policy under growing climate uncertainty.

Eva Fernandez Rodriguez, Zachary C. Rowland, Roderik A. Overzier

Free space optical (FSO) communication using lasers is a rapidly developing field in telecommunications that can offer advantages over traditional radio frequency technology. For example, optical laser links may allow transmissions at far higher data rates, require less operating power and smaller systems and have a smaller risk of interception. In recent years, FSO laser links have been demonstrated, tested or integrated in a range of environments and scenarios. These include FSO links for terrestrial communication, between ground stations and cube-sats in low Earth orbit, between ground and satellite in lunar orbit, as part of scientific or commercial space relay networks, and deep space communications beyond the moon. The possibility of FSO links from and to the surface of Mars could be a natural extension of these developments. In this paper we evaluate some effects of the Martian atmosphere on the propagation of optical communication links, with an emphasis on the impact of dust on the total link budget. We use the output of the Mars Climate Database to generate maps of the dust optical depth for a standard Mars climatology, as well as for a warm (dusty) atmosphere. These dust optical depths are then extrapolated to a wavelength of 1.55 um, and translated into total slant path optical depths to calculate link budgets and availability statistics for a link between the surface and a satellite in a sun-synchronous orbit. The outcomes of this study are relevant to potential future missions to Mars that may require laser communications to or from its surface. For example, the results could be used to constrain the design of communication terminals suitable to the Mars environment, or to assess the link performance as a function of ground station location.

Fatemeh Parto Dezfooli, Mohammad Javad Valadan Zoej, Fahimeh Youssefi et al.

Zoonotic Cutaneous Leishmaniasis (ZCL) is a vector-borne disease (VBD) characterized by distinct spatiotemporal patterns. Accurate evaluation of ZCL risk patterns necessitates the utilization of comprehensive epidemiological and ecological data. This study proposes a hybrid model that integrates the advantages of geographic information systems (GIS) for trend analysis, remote sensing (RS) for environmental data extraction, and machine learning (ML) for ZCL risk assessment in Ilam Province, Iran. Utilizing data from 2014 to 2019, spatial and temporal patterns are investigated using Moran’s I, Getis-Ord Gi* statistics, and the Mann-Kendall (MK) test, while high-risk ZCL maps are generated through Extreme Gradient Boosting (XGBoost) and Random Forest (RF) models. The proposed model harnesses high-precision disease and environmental geospatial monitoring to address limitations of previous systems through robust, data-driven insights. The results reveal significant patterns, with a Moran’s I statistic of 0.68 (p < 0.01) and MK values of –2.254 for annual data (p = 0.024) and 3.340 for monthly data (p = 0.001). Temporal analysis indicates a declining trend, with peak incidence observed in late fall and early winter. Consequently, due to the incubation period, the critical infection period occurs during summer. The risk maps demonstrate high levels of accuracy (area under the curve of 0.96 for RF and 0.98 for XGBoost), pinpointing high-risk areas in the western and southern hot deserts and low-risk regions in the northeastern mountainous areas. Moreover, there is an increasing trend in high-risk zones, corresponding to rising temperatures across different cities and seasons. These findings highlight a significant relationship between ZCL spread and temperature-related factors, offering valuable insights for future research.

Getachew Tadesse, Mulugeta Lemenih, Teshale Woldeamanuel et al.

Incorporating large-scale climate indices like the El Niño/Southern Oscillation (ENSO) is essential for understanding climate variability and change on a finer scale. Therefore, this study aimed to investigate the trends and magnitude of climate variability and change in the Kembata Tembaro zone in Southern Ethiopia. Climate data from the Kadida Gamella (KG), Kacha Birra (KB), and Hadaro Tunto (HT) stations were collected. The coefficient of variation (CV), standardized anomaly index (SAI), and standard precipitation index (SPI) were used to assess the climate variability. The Pearson product moment correlation was used to determine the association between rainfall variability and ENSO. In addition, the Mann–Kendall (MK) trend test was used to assess climate trends. The results revealed that rainfall variability was observed between seasons, with CVs ranging from 14.1% to 25.0%. Higher percentages of dry (negative) rainfall anomaly values over time were estimated during the Kiremt (June–September) (51.6%) and Belg (February–May) (53.8%) seasons, indicating an increase in the number of dry years. These findings show that droughts have become more frequent and severe in the study area. Additionally, ENSO strongly influences both Kiremt and Belg rainfall amounts. However, some of the stations had significant (p<0.05) positive trends in Kiremt for KB and HT as well as in annual rainfall for KB. Furthermore, annual and seasonal temperature trends showed significant (p<0.05) increasing trends at all stations. The average rates of change for the maximum and minimum annual temperatures were 0.029 and 0.030°C, respectively. Overall, the findings showed that over the past 31 years, the study area has experienced significant fine-scale climatic variability and change. This suggests that microscale analysis of trends and magnitude of climate variability and change could be useful for developing context-specific adaptation strategies.

Juan Nathaniel, Yongquan Qu, Tung Nguyen et al.

Accurate prediction of climate in the subseasonal-to-seasonal scale is crucial for disaster preparedness and robust decision making amidst climate change. Yet, forecasting beyond the weather timescale is challenging because it deals with problems other than initial condition, including boundary interaction, butterfly effect, and our inherent lack of physical understanding. At present, existing benchmarks tend to have shorter forecasting range of up-to 15 days, do not include a wide range of operational baselines, and lack physics-based constraints for explainability. Thus, we propose ChaosBench, a challenging benchmark to extend the predictability range of data-driven weather emulators to S2S timescale. First, ChaosBench is comprised of variables beyond the typical surface-atmospheric ERA5 to also include ocean, ice, and land reanalysis products that span over 45 years to allow for full Earth system emulation that respects boundary conditions. We also propose physics-based, in addition to deterministic and probabilistic metrics, to ensure a physically-consistent ensemble that accounts for butterfly effect. Furthermore, we evaluate on a diverse set of physics-based forecasts from four national weather agencies as baselines to our data-driven counterpart such as ViT/ClimaX, PanguWeather, GraphCast, and FourCastNetV2. Overall, we find methods originally developed for weather-scale applications fail on S2S task: their performance simply collapse to an unskilled climatology. Nonetheless, we outline and demonstrate several strategies that can extend the predictability range of existing weather emulators, including the use of ensembles, robust control of error propagation, and the use of physics-informed models. Our benchmark, datasets, and instructions are available at https://leap-stc.github.io/ChaosBench.

Giovanni Ziarelli, Stefano Pagani, Nicola Parolini et al.

In this work, we aim to formalize a novel scientific machine learning framework to reconstruct the hidden dynamics of the transmission rate, whose inaccurate extrapolation can significantly impair the quality of the epidemic forecasts, by incorporating the influence of exogenous variables (such as environmental conditions and strain-specific characteristics). We propose an hybrid model that blends a data-driven layer with a physics-based one. The data-driven layer is based on a neural ordinary differential equation that learns the dynamics of the transmission rate, conditioned on the meteorological data and wave-specific latent parameters. The physics-based layer, instead, consists of a standard SEIR compartmental model, wherein the transmission rate represents an input. The learning strategy follows an end-to-end approach: the loss function quantifies the mismatch between the actual numbers of infections and its numerical prediction obtained from the SEIR model incorporating as an input the transmission rate predicted by the neural ordinary differential equation. We validate this original approach using both a synthetic test case and a realistic test case based on meteorological data (temperature and humidity) and influenza data from Italy between 2010 and 2020. In both scenarios, we achieve low generalization error on the test set and observe strong alignment between the reconstructed model and established findings on the influence of meteorological factors on epidemic spread. Finally, we implement a data assimilation strategy to adapt the neural equation to the specific characteristics of an epidemic wave under investigation, and we conduct sensitivity tests on the network hyperparameters.

Mark DeMaria, James L. Franklin, Galina Chirokova et al.

In just the past few years multiple data-driven Artificial Intelligence Weather Prediction (AIWP) models have been developed, with new versions appearing almost monthly. Given this rapid development, the applicability of these models to operational forecasting has yet to be adequately explored and documented. To assess their utility for operational tropical cyclone (TC) forecasting, the NHC verification procedure is used to evaluate seven-day track and intensity predictions for northern hemisphere TCs from May-November 2023. Four open-source AIWP models are considered (FourCastNetv1, FourCastNetv2-small, GraphCast-operational and Pangu-Weather). The AIWP track forecast errors and detection rates are comparable to those from the best-performing operational forecast models. However, the AIWP intensity forecast errors are larger than those of even the simplest intensity forecasts based on climatology and persistence. The AIWP models almost always reduce the TC intensity, especially within the first 24 h of the forecast, resulting in a substantial low bias. The contribution of the AIWP models to the NHC model consensus was also evaluated. The consensus track errors are reduced by up to 11% at the longer time periods. The five-day NHC official track forecasts have improved by about 2% per year since 2001, so this represents more than a five-year gain in accuracy. Despite substantial negative intensity biases, the AIWP models have a neutral impact on the intensity consensus. These results show that the current formulation of the AIWP models have promise for operational TC track forecasts, but improved bias corrections or model reformulations will be needed for accurate intensity forecasts.

Jan Martinů, Petr Šimánek

This study investigates the application of deep-learning diffusion models for the super-resolution of weather data, a novel approach aimed at enhancing the spatial resolution and detail of meteorological variables. Leveraging the capabilities of diffusion models, specifically the SR3 and ResDiff architectures, we present a methodology for transforming low-resolution weather data into high-resolution outputs. Our experiments, conducted using the WeatherBench dataset, focus on the super-resolution of the two-meter temperature variable, demonstrating the models' ability to generate detailed and accurate weather maps. The results indicate that the ResDiff model, further improved by incorporating physics-based modifications, significantly outperforms traditional SR3 methods in terms of Mean Squared Error (MSE), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR). This research highlights the potential of diffusion models in meteorological applications, offering insights into their effectiveness, challenges, and prospects for future advancements in weather prediction and climate analysis.

Nitin Sagar Boyeena, Begari Susheel Kumar

Time series forecasting is crucial in several sectors, such as meteorology, retail, healthcare, and finance. Accurately forecasting future trends and patterns is crucial for strategic planning and making well-informed decisions. In this case, it is crucial to include many forecasting methodologies. The strengths of Auto-regressive Integrated Moving Average (ARIMA) for linear time series, Seasonal ARIMA models (SARIMA) for seasonal time series, Exponential Smoothing State Space Models (ETS) for handling errors and trends, and Long Short-Term Memory (LSTM) Neural Network model for complex pattern recognition have been combined to create a comprehensive framework called FlowScope. SARIMA excels in capturing seasonal variations, whereas ARIMA ensures effective handling of linear time series. ETS models excel in capturing trends and correcting errors, whereas LSTM networks excel in reflecting intricate temporal connections. By combining these methods from both machine learning and deep learning, we propose a deep-hybrid learning approach FlowScope which offers a versatile and robust platform for predicting time series data. This empowers enterprises to make informed decisions and optimize long-term strategies for maximum performance. Keywords: Time Series Forecasting, HybridFlow Forecast Framework, Deep-Hybrid Learning, Informed Decisions.

S. Chaaraoui, S. Houben, S. Meilinger

<p>This work proposes a novel approach for probabilistic end-to-end all-sky imager-based nowcasting with horizons of up to 30 min using an ImageNet pre-trained deep neural network. The method involves a two-stage approach. First, a backbone model is trained to estimate the irradiance from all-sky imager (ASI) images. The model is then extended and retrained on image and parameter sequences for forecasting. An open access data set is used for training and evaluation. We investigated the impact of simultaneously considering global horizontal (GHI), direct normal (DNI), and diffuse horizontal irradiance (DHI) on training time and forecast performance as well as the effect of adding parameters describing the irradiance variability proposed in the literature. The backbone model estimates current GHI with an RMSE and MAE of 58.06 and 29.33 W m<span class="inline-formula">⁻²</span>, respectively. When extended for forecasting, the model achieves an overall positive skill score reaching 18.6 % compared to a smart persistence forecast. Minor modifications to the deterministic backbone and forecasting models enables the architecture to output an asymmetrical probability distribution and reduces training time while leading to similar errors for the backbone models. Investigating the impact of variability parameters shows that they reduce training time but have no significant impact on the GHI forecasting performance for both deterministic and probabilistic forecasting while simultaneously forecasting GHI, DNI, and DHI reduces the forecast performance.</p>

Claudia Espinosa Valdés, Evelio García Valdés, Rosemary López Le

En Cuba, tanto en la costa norte como en la sur, la presencia de sargazos ha ocurrido y se ha reportado desde varios ángulos de observación por distintos autores. Estas macroalgas provocan un aumento de la mortalidad de varias especies marinas como peces, tortugas marinas e invertebrados costeros y pueden ser un severo impacto para la pesca local, la acuicultura y el turismo. Es por ello, que resulta de gran importancia conocer las condiciones atmosféricas favorables para el desplazamiento del sargazo. Teniendo en cuenta lo anterior, se plantea como objetivo principal analizar los Tipos de Situaciones Sinópticas favorables para el arribo de sargazos a las costas cubanas. En este artículo se utilizó la clasificación de los Tipos de Situaciones Sinópticas elaborada por Lapinel en 1988. Se demostró que la situación sinóptica que influye con mayor frecuencia en el archipiélago cubano es el anticiclón continental migratorio, seguidamente del anticiclón oceánico subtropical y del flujo anticiclónico extendido. Además, se mostró que los vientos del primer y segundo cuadrante, impuestos por los sistemas de altas presiones, son factores importantes en la llegada de sargazos a los litorales cubanos. Por otra parte, se comprobó que la costa sur de Cuba se ve más afectada por la llegada de sargazos que la costa norte, siendo la región oriental la que presentó un número mayor de reportes de arribo de estas macroalgas, principalmente, la provincia Guantánamo. También, se evidenció que en el período lluvioso (mayo - octubre) las costas cubanas se ven más afectadas por el arribo de sargazos, siendo los meses junio y septiembre los más representativos.

Liran Peng, Peter N. Blossey, Walter M. Hannah et al.

High-Resolution Multi-scale Modeling Frameworks (HR) -- global climate models that embed separate, convection-resolving models with high enough resolution to resolve boundary layer eddies -- have exciting potential for investigating low cloud feedback dynamics due to reduced parameterization and ability for multidecadal throughput on modern computing hardware. However low clouds in past HR have suffered a stubborn problem of over-entrainment due to an uncontrolled source of mixing across the marine subtropical inversion manifesting as stratocumulus dim biases in present-day climate, limiting their scientific utility. We report new results showing that this over-entrainment can be partly offset by using hyperviscosity and cloud droplet sedimentation. Hyperviscosity damps small-scale momentum fluctuations associated with the formulation of the momentum solver of the embedded LES. By considering the sedimentation process adjacent to default one-moment microphysics in HR, condensed phase particles can be removed from the entrainment zone, which further reduces entrainment efficiency. The result is an HR that is able to produce more low clouds with a higher liquid water path and a reduced stratocumulus dim bias. Associated improvements in the explicitly simulated sub-cloud eddy spectrum are observed. We report these sensitivities in multi-week tests and then explore their operational potential alongside microphysical retuning in decadal simulations at operational 1.5 degree exterior resolution. The result is a new HR having desired improvements in the baseline present-day low cloud climatology, and a reduced global mean bias and root mean squared error of absorbed shortwave radiation. We suggest it should be promising for examining low cloud feedbacks with minimal approximation.

Binqing Wu, Weiqi Chen, Wengwei Wang et al.

Due to insufficient local area information, numerical weather prediction (NWP) may yield biases for specific areas. Previous studies correct biases mainly by employing handcrafted features or applying data-driven methods intuitively, overlooking the complicated dependencies between weather factors and between areas. To address this issue, we propose WeatherGNN, a local NWP bias-correction method that utilizes Graph Neural Networks (GNNs) to exploit meteorological dependencies and spatial dependencies under the guidance of domain knowledge. Specifically, we introduce a factor GNN to capture area-specific meteorological dependencies adaptively based on spatial heterogeneity and a fast hierarchical GNN to capture dynamic spatial dependencies efficiently guided by Tobler's first and second laws of geography. Our experimental results on two real-world datasets demonstrate that WeatherGNN achieves the state-of-the-art performance, outperforming the best baseline with an average of 4.75 \% on RMSE.

P. Hoffmann, P. Hoffmann, V. Reinhart et al.

<p>Anthropogenic land use and land cover change (LULCC) is a major driver of environmental changes. The biophysical impacts of these changes on the regional climate in Europe are currently being extensively investigated within the World Climate Research Program (WCRP) Coordinated Downscaling Experiment (CORDEX) Flagship Pilot Study (FPS) Land Use and Climate Across Scales (LUCAS) using an ensemble of different regional climate models (RCMs) coupled with diverse land surface models (LSMs). In order to investigate the impact of realistic LULCC on past and future climates, high-resolution datasets with observed LULCC and projected future LULCC scenarios are required as input for the RCM–LSM simulations. To account for these needs, we generated the LUCAS Land Use and land Cover change (LUC) dataset version 1.1 at 0.1<span class="inline-formula">^∘</span> resolution for Europe with annual LULC maps from 1950 to 2100 (<a href="https://doi.org/10.26050/WDCC/LUC_hist_EU_v1.1">https://doi.org/10.26050/WDCC/LUC_hist_EU_v1.1</a>, <span class="cit" id="xref_altparen.1"><a href="#bib1.bibx35">Hoffmann et al.</a>, <a href="#bib1.bibx35">2022</a><a href="#bib1.bibx35">b</a></span>, <a href="https://doi.org/10.26050/WDCC/LUC_future_EU_v1.1">https://doi.org/10.26050/WDCC/LUC_future_EU_v1.1</a>, <span class="cit" id="xref_altparen.2"><a href="#bib1.bibx34">Hoffmann et al.</a>, <a href="#bib1.bibx34">2022</a><a href="#bib1.bibx34">a</a></span>), which is tailored to use in state-of-the-art RCMs. The plant functional type (PFT) distribution for the year 2015 (i.e. the Modelling human LAND surface Modifications and its feedbacks on local and regional cliMATE – LANDMATE – PFT dataset) is derived from the European Space Agency Climate Change Initiative Land Cover (ESA-CCI LC) dataset. Details on the conversion method, cross-walking procedure, and evaluation of the LANDMATE PFT dataset are given in the companion paper by <span class="cit" id="xref_text.3"><a href="#bib1.bibx68">Reinhart et al.</a> (<a href="#bib1.bibx68">2022</a><a href="#bib1.bibx68">b</a>)</span>. Subsequently, we applied the land use change information from the Land-Use Harmonization 2 (LUH2) dataset, provided at 0.25<span class="inline-formula">^∘</span> resolution as input for Coupled Modelling Intercomparison Project Phase 6 (CMIP6) experiments, to derive LULC distributions at<span id="page3820"/> high spatial resolution and at annual time steps from 1950 to 2100. In order to convert land use and land management change information from LUH2 into changes in the PFT distribution, we developed a land use translator (LUT) specific to the needs of RCMs. The annual PFT maps for Europe for the period 1950 to 2015 are derived from the historical LUH2 dataset by applying the LUT backward from 2015 to 1950. Historical changes in the forest type changes are considered using an additional European forest species dataset. The historical changes in the PFT distribution of LUCAS LUC follow closely the land use changes given by LUH2 but differ in some regions compared to other annual LULCC datasets. From 2016 onward, annual PFT maps for future land use change scenarios based on LUH2 are derived for different shared socioeconomic pathway (SSP) and representative concentration pathway (RCP) combinations used in the framework of CMIP6. The resulting LULCC maps can be applied as land use forcing to the new generation of RCM simulations for downscaling of CMIP6 results. The newly developed LUT is transferable to other CORDEX regions worldwide.</p>

Theophilus Bright Ogbuabia, Mert Guney, Nassiba Baimatova et al.

According to the World Health Organization, Kazakhstan is one of the most polluted countries in the world. PM_2.5, a major air pollutant, is six times higher than the recommended value of 5 mg/m³. The government has implemented measures to reduce air pollution, such as introducing green energy-powered buses for public transportation, but the results have not been sufficient. Therefore, it is necessary to investigate the sources of PM_2.5. This study involved simulating the Combined Heat and Power Plants (CHPPs) emissions in Almaty using AERMOD and WRF for two weeks in January 2021. Two scenarios were performed: controlled and uncontrolled. The results showed that if the control mechanism of the CHPP functions at maximum efficiency, the impact of the CHPP emissions on the total emission concentration will be negligible, which is about 6% on average. However, for uncontrolled CHPPs, the emissions will contribute from 30% to 39% on average to the total PM_2.5 concentration when compared with data from US Embassy monitoring stations and public air quality monitoring network, which use Pms5003 PM2.5 sensors.

Christian Sigg, Flavia Cavallaro, Tobias Günther et al.

Outdoor webcam images are an information-dense yet accessible visualization of past and present weather conditions, and are consulted by meteorologists and the general public alike. Weather forecasts, however, are still communicated as text, pictograms or charts. We therefore introduce a novel method that uses photographic images to also visualize future weather conditions. This is challenging, because photographic visualizations of weather forecasts should look real, be free of obvious artifacts, and should match the predicted weather conditions. The transition from observation to forecast should be seamless, and there should be visual continuity between images for consecutive lead times. We use conditional Generative Adversarial Networks to synthesize such visualizations. The generator network, conditioned on the analysis and the forecasting state of the numerical weather prediction (NWP) model, transforms the present camera image into the future. The discriminator network judges whether a given image is the real image of the future, or whether it has been synthesized. Training the two networks against each other results in a visualization method that scores well on all four evaluation criteria. We present results for three camera sites across Switzerland that differ in climatology and terrain. We show that users find it challenging to distinguish real from generated images, performing not much better than if they guessed randomly. The generated images match the atmospheric, ground and illumination conditions of the COSMO-1 NWP model forecast in at least 89 % of the examined cases. Nowcasting sequences of generated images achieve a seamless transition from observation to forecast and attain visual continuity.

Yuya Baba

Abstract Hindcast experiments were performed for heavy rainfall events over Japan in July 2020 using a regional atmospheric model and a regional coupled model to examine the importance of ocean prediction for predicting heavy rainfall events. Both models were able to predict the first peak of accumulated rainfall over western Japan occurring in the first half of July. However, only the coupled model predicted the second peak that occurred in the second half of July. Sea level pressure (SLP) and low‐level moisture inflow originating from an existing atmospheric river (AR) were found to differ in each model. In the regional atmospheric model, the error associated with the inaccurate low‐level moisture inflow grew with rising excessive latent heat flux, which enhanced convection and resulted in incorrect SLP patterns. This trend seems to be enhanced by having a prescribed sea surface temperature (SST), which affects the surface heat flux. When ocean conditions are predicted as in the coupled model, such error growth is suppressed by changes in SST that adjust surface heat flux, and it leads to generation of the correct SLP patterns. With correct SLP especially for Pacific high in this case, favorable conditions for inflow from the AR can also be predicted, thus making it possible to predict the heavy rainfall. In conclusion, considering the atmospheric feedback on SST, ocean prediction can improve the predictability of heavy rainfall over Japan, the conditions for which are influenced by the nearby AR. Ocean prediction may therefore extend the range of weather forecasting.

Linda Rudolph, Naomi Beyeler, Lisa Patel

Yang Han, Qi Zhang, Victor O. K. Li et al.

Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon effect and high building density. Whilst accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models fail to fully address the complex interaction between air pollution and urban dynamics. Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast. Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect. Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models. Our model attains an accuracy of 67.6%, 77.2%, and 66.1% in fine-grained hourly estimation, 1-hr, and 24-hr air pollution forecast for Hong Kong, and an accuracy of 65.0%, 75.3%, and 63.5% for Beijing. Our saliency analysis has revealed that for Hong Kong, street canyon and road density are the best estimators for NO2, while meteorology is the best estimator for PM2.5.

Stephen Harvey, Mingchu Zhang, Gilberto J. Fochesatto

Recent accelerations of climate warmings can open agricultural opportunities in the region of Interior Alaska. In this paper, a simulation of spring wheat growth forced with projected climate scenarios was conducted by the Decision Support System for Agrotechnology Transfer (DSSAT) crop model. The model was calibrated and validated using experimental data.Using an Alaskan cultivar (cv.) Ingal and a baseline covering 1989–2018, projected changes in days to maturity and yield were simulated following the Representative Concentration Pathways (RCP) 4.5 (medium–low emissions) and RCP8.5 (high emissions) climate change scenarios. For each RCP scenario, spring wheat growth was simulated in the time series covering 2020–2049 (indicated as 2035 s), 2050–2079 (2065 s), and 2080–2099 (2090 s). The baseline value of days to maturity was 69 and yield resulted in 1956 kg ha−1. Results show that under RCP4.5 and RCP8.5 2035 s, 2065 s, and 2090 s scenarios, days to maturity decrease, ranging from 64 to 55 days, and changes in yield range from a 3% increase to a 6% decrease.Adaptation by increasing the cultivar’s growing degree day requirement resulted in 69 and 68 days to maturity in RCP4.5 2035 s and RCP8.5 2035 s, respectively, which in turn increased yields 5% and 7%, respectively. Increased soil water at planting from 80 to 85% field capacity, due to increased annual precipitation, resulted in additional yield increases. This indicates that selecting spring wheat varieties to maintain similar baseline days to maturity and agronomic practices that store fall/winter precipitation are of importance to materialize future spring wheat yield increases of Interior Alaska.