Search

This paper evaluated and compared the performance of a statistical downscaling method and a dynamical downscaling method to simulate the spatial–temporal rainfall distribution. Outputs from RegCM4 Regional Climate Model (RCM) and the CanESM2 Atmosphere–Ocean General Circulation Model (AOGCM) were selected for the data scarce Gwadar‐Ormara basin, Pakistan. The evaluation was based on the climatological average and standard deviation for historic (1971–2000) and future (2041–2070) time periods under Representative Concentration Pathways (RCP) 4.5 and 8.5 scenarios. The performance evaluation showed that statistical downscaling is preferred to simulate and project rainfall patterns in the study area. Additionally, the Statistical DownScaling Model (SDSM) showed low R2 values in calibration and validation of the simulations with respect to observed data for the historic period. Overall, SDSM generated satisfactory results in simulating the monthly rainfall cycle of the entire basin. In this study, RegCM4 showed large rainfall errors and missed one rainfall season in the historic period. This study also explored whether the grid‐based rainfall time series of the Asian Precipitation—Highly Resolved Observational Daily Integration Towards Evaluation (APHRODITE) dataset could be used to enlarge and complement the sample of in situ observed rainfall time series. A spatial correlogram was used for observed and APHRODITE rainfall data to assess the consistency between the two data sources, which resulted in rejecting APHRODITE data. For the future time period (2041–2070) under RCPs 4.5 and 8.5 scenarios, rainfall projections did not show significant difference for both downscaling approaches. This may relate to the driving model (CanESM2 AOGCM) and not necessarily suggests poor performance of downscaling; either statistical or dynamical. Hence, the study recommends evaluating a multi‐model ensemble including other GCMs and RCMs for the same area of study. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has emerged as a promising tool to downscale climate projections at regional‐to‐local scales from large‐scale atmospheric fields following the perfect‐prognosis approach. Given their complexity, it is crucial to properly evaluate these methods, especially when applied to changing climatic conditions where the ability to extrapolate/generalize is key. In this work, we intercompare several DL models extracted from the literature for the same challenging use‐case (downscaling temperature in the CORDEX North America domain) and expand standard evaluation methods building on eXplainable Artificial Intelligence (XAI) techniques. Specifically, we introduce two novel XAI‐based diagnostics—Aggregated Saliency Map and Saliency Dispersion Maps—and show how they can be used to unravel the internal behavior of these models, aiding in their design and evaluation. This work advocates for the introduction of XAI techniques into deep downscaling evaluation frameworks, especially when working with large regions and/or under climate change conditions. Plain Language Summary: Due to limitations in the computational resources available, General Circulation Models (GCMs) are often used to simulate the climate system over coarse resolution grids. This hampers the applicability of GCM products in the regional‐to‐local scale, highly demanded by different socio‐economic sectors. Statistical downscaling aims to solve this problem by generating high‐resolution climate fields. Recently, machine learning techniques—particularly deep learning (DL) models—have shown promising results in this task. These models are first trained in a historical period through observational data sets, and then applied to the GCM outputs of plausible future scenarios, thus generating high‐resolution climate change products. To assess the performance of these methods, a number of evaluation metrics have been proposed considering both the skill to reproduce present climate conditions and the ability to generalize changing conditions. Here, we illustrate the possibilities of eXplainable Artificial Intelligence (XAI) techniques to expand the evaluation framework for deep downscaling methods, introducing new XAI‐derived diagnostics to unravel their internal behavior. The results show the usefulness of incorporating XAI techniques into statistical downscaling evaluation frameworks, especially when working with large regions and/or under climate change conditions. Key Points: Explainable artificial intelligence (XAI) facilitates the evaluation of deep downscaling models by unraveling their internal behaviorXAI techniques can detect structural problems not revealed by standard evaluation, which may be relevant for understanding model differencesXAI techniques can assess the relevance and locality of the predictors of deep learning models, helping to assess their physical consistency [ABSTRACT FROM AUTHOR]

Climate scenario data set are indispensable for assessing future climate impacts. In this study, we developed statistically downscaled climate scenarios in Japan using modified bias correction method based on five general circulation models selected from the Coupled Model Intercomparison Project (CMIP) Phase 6 to facilitate impact assessments and adaptation strategies. Modification of time window of the original correction method results in successful agreement with the observed seasonal change of variables in each grid. The original CMIP6 models have a relatively small bias compared to CMIP5 models. The advantage of CMIP6‐based bias‐corrected scenarios is its availability for multiple global circulation models, which covered wide uncertainty in CMIP6 ensembles, with various emissions scenarios for representative concentration pathway (RCP) including RCP4.5, RCP2.6, and RCP8.5. Several temperature‐related indices derived from the CMIP6‐based climate scenarios agreed well with observations. The number of extremely hot days and nights increased nonlinearly in the future with additional global warming. An increase in the global warming level from 1 to 2°C above the early 1900s would increase the probability of the number of extremely hot days per year exceeding the 2018 case by 4.1 times. The development of bias‐corrected climate scenarios facilitates the study of various climate impacts on a CMIP6 basis. Plain Language Summary: It is important to appropriately remove model biases since the impact of climate change does not always depend linearly on the climate input data. To facilitate impact assessment based on the latest data set from CMIP6, we developed bias‐corrected daily climate scenarios for eight variables using five models. The application of climate scenarios to heat mortality‐related indices showed that they reproduced historical values well and would be useful for future projections. Key Points: We developed a statistically downscaled climate scenario in Japan based on five general circulation models selected from the Coupled Model Intercomparison Project Phase 6 to facilitate impact assessmentsSimilar increasing trend was found for the temperature and precipitation between CMIP5‐ and CMIP6‐based climate scenarios, while CMIP6‐based scenario showed smaller biases for the underlying global circulation model. Addition of the moderate emission scenario for CMIP6‐based scenario enable us to consider wider range of the possible futureSeveral threshold‐based indices derived from the climate scenarios was evaluated. They agreed with the observed values for the historical period. For the future, we can discuss the possible future change of indices in comparison with the historical values. Development of the bias‐corrected climate scenarios has enabled the broader impact assessment community in Japan to study various climate impacts on a CMIP6 basis [ABSTRACT FROM AUTHOR]