Tag: Climate Change Downscaling Techniques

Abstract

Global climate models (GCMs) and Earth system models (ESMs) exhibit biases, with resolutions too coarse to capture local variability for fine-scale, reliable drought and climate impact assessment. However, conventional bias correction approaches may cause implausible climate change signals due to unrealistic representations of spatial and intervariable dependences. While purely data-driven deep learning has achieved significant progress in improving climate and earth system simulations and predictions, they cannot reliably learn the circumstances (e.g., extremes) that are largely unseen in historical climate but likely becoming more frequent in the future climate (i.e., climate non-stationarity). This study shows an integrated trend-preserving deep learning approach that can address the spatial and intervariable dependences and climate non-stationarity issues for downscaling and bias correcting GCMs/ESMs. Here we combine the super-resolution deep residual network (SRDRN) with the trend-preserving quantile delta mapping (QDM) to downscale and bias correct six primary climate variables at once (including daily precipitation, maximum temperature, minimum temperature, relative humidity, solar radiation, and wind speed) from five state-of-the-art GCMs/ESMs in the Coupled Model Intercomparison Project Phase 6 (CMIP6). We found that the SRDRN-QDM approach greatly reduced GCMs/ESMs biases in spatial and intervariable dependences while significantly better-reducing biases in extremes compared to deep learning. The estimated drought based on the six bias-corrected and downscaled variables captured the observed drought intensity and frequency, which outperformed state-of-the-art multivariate bias correction approaches, demonstrating its capability for correcting GCMs/ESMs biases in spatial and multivariable dependences and extremes.

Abstract

This paper evaluates the NASA Earth Exchange Global Daily Downscaled Projections’ (NEX-GDDP) CMIP6 models’ performance in simulating extreme climate indices across China and its eight subregions for the period 2081–2100 under SSP1-2.6, SSP2-4.5 and SSP5-8.5 scenarios. The models effectively reproduce the spatial patterns of extreme high temperatures, especially in northern China. They show enhanced capabilities in accurately simulating the maximum daily maximum temperature (TXx) and the number of high temperature days (T35). They improve the cold bias of the TXx index in Northwest China and warm bias in South China. In terms of precipitation, the models demonstrate strong performance, evidenced by significant spatial correlations in total wet day precipitation (PTOT) simulations. They reduce the biases of PTOT and simple daily intensity (SDII) compared to CMIP6 models. Regionally, they enhance PTOT accuracy along southern coasts and in Yunnan, better captures very heavy precipitation days (R20) in the Southwest region, max 5-day precipitation (RX5D) in North China and Southwest region, and SDII in the Northeast region and Yunnan. Under SSP5-8.5 scenario, significant impacts include increased TXx in Northwest China, more heatwave days in Southwest China, and more T35 in South China. Extreme precipitation will become more frequent in South and East China, with the greatest intensity increases in Southwest China (SWC1). North China will see fewest consecutive dry days (CDD) indices, while consecutive wet days (CWD) will prominently rise in SWC1.

Abstract

The continued threat from climate change and human impacts on water resources demands high-resolution and continuous hydrological data accessibility for predicting trends and availability. This study proposes a novel threefold downscaling method based on machine learning (ML) which integrates: data normalization; interaction of hydrometeorological variables; and the application of a time series split for cross-validation that produces a high spatial resolution groundwater storage anomaly (GWSA) dataset from the Gravity Recovery and Climate Experiment (GRACE) and its successor mission, GRACE Follow-On (GRACE-FO). In the study, the relationship between the terrestrial water storage anomaly (TWSA) from GRACE and other land surface and hydrometeorological variables (e.g., vegetation coverage, land surface temperature, precipitation, and in situ groundwater level data) is leveraged to downscale the GWSA. The predicted downscaled GWSA datasets were tested using monthly in situ groundwater level observations, and the results showed that the model satisfactorily reproduced the spatial and temporal variations in the GWSA in the study area, with Nash-Sutcliffe efficiency (NSE) correlation coefficient values of 0.8674 (random forest) and 0.7909 (XGBoost), respectively. Evapotranspiration was the most influential predictor variable in the random forest model, whereas it was rainfall in the XGBoost model. In particular, the random forest model excelled in aligning closely with the observed groundwater storage patterns, as evidenced by its high positive correlations and lower error metrics (Mean Absolute Error (MAE) of 54.78 mm; R-squared (R²) of 0.8674). The downscaled 5 km GWSA data (based on random forest) showed a decreasing trend in storage associated with variability in the rainfall pattern. An increase in drought severity during El Niño lengthened the full recovery time of groundwater based on historical storage trends. Furthermore, the time lag between the occurrence of precipitation and recharge was likely controlled by the drought intensity and the spatial recharge characteristics of the aquifer. Projected increases in drought severity could further increase groundwater recovery times in response to droughts in a changing climate, resetting storage to a new tipping condition. Therefore, climate change adaptation strategies must recognise that less groundwater will be available to supplement the surface water supply during droughts.

Abstract

This research investigates the changes in flash flood susceptibility in Algiers, Northern Algeria between current and future climatic conditions based on two Shared Socio-economic Pathways (SSP2-4.5 and SSP3-7.0) from the CMIP6 dataset. Three machine-learning models, namely the Generalized Linear Model (GLM), Random Forest (RF) and Gradient Boosting Machine (GBM), were employed to assess flash flood susceptibility by capturing the relationships between a set of predictive variables and historical flash flood events in the study area. The validity of the used models was assessed using the receiver operating characteristic (ROC) model and its area under the curve (AUC). This yielded excellent performance for all models with a slight superiority to GBM (AUC = 96.4%) compared to RF (AUC = 96.1%) and GLM (AUC = 93.9%). With respct to the year 2018, SSP 2–4.5 revealed a future evolution of high to very high flash flood susceptibility of + 2.9% by the year 2040, + 1.6% by 2060 and + 5.1% by 2080. Under SSP3-7.0, the spatial coverage of high and very high susceptibility classes showed more significant increase of 3.6% by 2040, + 4.9% by 2060, and + 4.7% by 2080. Overall, this research provided insights into the changes in flash flood susceptibility between current and two future climate change scenarios. This can help decision makers and urban planners in Algiers in developing adequate strategies to improve resilience against future flash floods.

Abstract

Atmospheric aerosols partly compensate for the warming due to greenhouse gases by perturbing the radiation balance of the Earth–Atmosphere system. In this study, the impacts of aerosols on surface temperature are examined over the Indo-Gangetic Plain (IGP) and Himalayan Tibetan Plateau (HTP), where diverse aerosol and climatic conditions prevail. Both regions have significant impacts on the regional climate and hydrological cycles in South Asia. The IGP experiences high aerosol loading throughout the year and is expected to affect surface temperature significantly. In contrast, the HTP exhibits relatively pristine or lower aerosol loading, whose effects on surface temperature are highly uncertain due to snow albedo feedback. Climate model simulations are used to decompose the surface temperature changes due to aerosol forcing to its radiative and non-radiative components over the IGP and HTP. The shortwave cooling due to aerosols is mostly compensated by the decrease in sensible heat over the IGP. On the other hand, HTP experiences surface cooling due to the direct effects and surface warming due to aerosol-induced snow-darkening effects (deposition of absorbing aerosols on snow). The net effect of aerosols on shortwave radiation is further redistributed into non-radiative heat fluxes. This study provides a better understanding of aerosol-induced surface temperature change and its partitioning into radiative and non-radiative components.

Abstract

Atmospheric aerosols partly compensate for the warming due to greenhouse gases by perturbing the radiation balance of the Earth–Atmosphere system. In this study, the impacts of aerosols on surface temperature are examined over the Indo-Gangetic Plain (IGP) and Himalayan Tibetan Plateau (HTP), where diverse aerosol and climatic conditions prevail. Both regions have significant impacts on the regional climate and hydrological cycles in South Asia. The IGP experiences high aerosol loading throughout the year and is expected to affect surface temperature significantly. In contrast, the HTP exhibits relatively pristine or lower aerosol loading, whose effects on surface temperature are highly uncertain due to snow albedo feedback. Climate model simulations are used to decompose the surface temperature changes due to aerosol forcing to its radiative and non-radiative components over the IGP and HTP. The shortwave cooling due to aerosols is mostly compensated by the decrease in sensible heat over the IGP. On the other hand, HTP experiences surface cooling due to the direct effects and surface warming due to aerosol-induced snow-darkening effects (deposition of absorbing aerosols on snow). The net effect of aerosols on shortwave radiation is further redistributed into non-radiative heat fluxes. This study provides a better understanding of aerosol-induced surface temperature change and its partitioning into radiative and non-radiative components.

Abstract

Although Artificial Intelligence (AI) projects are common and desired by many institutions and research teams, there are still relatively few success stories of AI in practical use for the Earth science community. Many AI practitioners in Earth science are trapped in the prototyping stage and their results have not yet been adopted by users. Many scientists are still hesitating to use AI in their research routine. This paper aims to capture the landscape of AI-powered geospatial data sciences by discussing the current and upcoming needs of the Earth and environmental community, such as what practical AI should look like, how to realize practical AI based on the current technical and data restrictions, and the expected outcome of AI projects and their long-term benefits and problems. This paper also discusses unavoidable changes in the near future concerning AI, such as the fast evolution of AI foundation models and AI laws, and how the Earth and environmental community should adapt to these changes. This paper provides an important reference to the geospatial data science community to adjust their research road maps, find best practices, boost the FAIRness (Findable, Accessible, Interoperable, and Reusable) aspects of AI research, and reasonably allocate human and computational resources to increase the practicality and efficiency of Earth AI research.

Abstract

Although Artificial Intelligence (AI) projects are common and desired by many institutions and research teams, there are still relatively few success stories of AI in practical use for the Earth science community. Many AI practitioners in Earth science are trapped in the prototyping stage and their results have not yet been adopted by users. Many scientists are still hesitating to use AI in their research routine. This paper aims to capture the landscape of AI-powered geospatial data sciences by discussing the current and upcoming needs of the Earth and environmental community, such as what practical AI should look like, how to realize practical AI based on the current technical and data restrictions, and the expected outcome of AI projects and their long-term benefits and problems. This paper also discusses unavoidable changes in the near future concerning AI, such as the fast evolution of AI foundation models and AI laws, and how the Earth and environmental community should adapt to these changes. This paper provides an important reference to the geospatial data science community to adjust their research road maps, find best practices, boost the FAIRness (Findable, Accessible, Interoperable, and Reusable) aspects of AI research, and reasonably allocate human and computational resources to increase the practicality and efficiency of Earth AI research.

Abstract

Precipitation extremes have surged in frequency and duration in recent decades, significantly impacting various sectors, including agriculture, water resources, energy, and public health worldwide. Pakistan, being highly susceptible to climate change and extremes, has experienced adverse events in recent times, emphasizing the need for a comprehensive investigation into the relationship between precipitation extremes and crops production. This study focuses on assessing the association between precipitation extremes on crops production, with a particular emphasis on the Punjab province, a crucial region for the country’s food production. The initial phase of the study involved exploring the associations between precipitation extremes and crops production for the duration of 1980–2014. Notably, certain precipitation extremes, such as maximum CDDs (consecutive dry days), R99p (extreme precipitation events), PRCPTOT (precipitation total) and SDII (simple daily intensity index) exhibited strong correlations with the production of key crops like wheat, rice, garlic, dates, moong, and masoor. In the subsequent step, four machine learning (ML) algorithms were trained and tested using observed daily climate data (including maximum and minimum temperatures and precipitation) alongside model reference data (1985–2014) as predictors. Gradient boosting machine (GBM) was selected for its superior performance and employed to project precipitation extremes for three distinct future periods (F1: 2025–2049, F2: 2050–2074, F3: 2075–2099) under the SSP2-4.5 and SSP5-8.5 derived from the CMIP6 (Coupled Model Intercomparison Project Phase 6) archive. The projection results indicated an increasing and decreasing trend in CWDs (maximum consecutive wet days) and CDDs, respectively, at various meteorological stations. Furthermore, R10mm (the number of days with precipitation equal to or exceeding 10 mm) and R25mm displayed an overall increasing trend at most of the stations, though some exhibited a decreasing trend. These trends in precipitation extremes have potential consequences, including the risk of flash floods and damage to agriculture and infrastructure. However, the study emphasizes that with proper planning, adaptation measures, and mitigation strategies, the potential losses and damages can be significantly minimized in the future.

Abstract

Precipitation extremes have surged in frequency and duration in recent decades, significantly impacting various sectors, including agriculture, water resources, energy, and public health worldwide. Pakistan, being highly susceptible to climate change and extremes, has experienced adverse events in recent times, emphasizing the need for a comprehensive investigation into the relationship between precipitation extremes and crops production. This study focuses on assessing the association between precipitation extremes on crops production, with a particular emphasis on the Punjab province, a crucial region for the country’s food production. The initial phase of the study involved exploring the associations between precipitation extremes and crops production for the duration of 1980–2014. Notably, certain precipitation extremes, such as maximum CDDs (consecutive dry days), R99p (extreme precipitation events), PRCPTOT (precipitation total) and SDII (simple daily intensity index) exhibited strong correlations with the production of key crops like wheat, rice, garlic, dates, moong, and masoor. In the subsequent step, four machine learning (ML) algorithms were trained and tested using observed daily climate data (including maximum and minimum temperatures and precipitation) alongside model reference data (1985–2014) as predictors. Gradient boosting machine (GBM) was selected for its superior performance and employed to project precipitation extremes for three distinct future periods (F1: 2025–2049, F2: 2050–2074, F3: 2075–2099) under the SSP2-4.5 and SSP5-8.5 derived from the CMIP6 (Coupled Model Intercomparison Project Phase 6) archive. The projection results indicated an increasing and decreasing trend in CWDs (maximum consecutive wet days) and CDDs, respectively, at various meteorological stations. Furthermore, R10mm (the number of days with precipitation equal to or exceeding 10 mm) and R25mm displayed an overall increasing trend at most of the stations, though some exhibited a decreasing trend. These trends in precipitation extremes have potential consequences, including the risk of flash floods and damage to agriculture and infrastructure. However, the study emphasizes that with proper planning, adaptation measures, and mitigation strategies, the potential losses and damages can be significantly minimized in the future.