Relative Operating Characteristic Research Articles

The First Operational Version of Taiwan Central Weather Bureau’s One-Tier Global Atmosphere–Ocean Coupled Forecast System for Seasonal Prediction

Abstract The first version of the Taiwan Central Weather Bureau one-tier (TCWB1T) fully coupled global atmospheric and oceanic modeling forecast system had been developed and implemented as a routine operation for seasonal prediction at Central Weather Bureau (CWB) in 2017, with a minor revision in 2020. Based on NCEP CFSv1, the global atmospheric model in NCEP CFSv1 was replaced by CWB’s atmospheric global spectral model (GSM) and coupled with the GFDL MOM3. Several parameters have been tested and tuned in the CWB atmospheric GSM, achieving an optimal configuration with better sea surface temperature (SST) predictions for integration more than one year. Using NCEP CFSR as the initial condition, TCWB1T conducted hindcasts from 1982 to 2011 and forecasts from 2012 to 2019 to analyze its performance. The results of these hindcasts and forecasts show that the TCWB1T can make useful predictions as verified against the observations of OISST, ERSST, CFSR, and GPCP based on the methods of EOF, RMSE, anomaly correlation, ranked probability skill score (RPSS), reliability diagram (RD), and relative operating characteristics (ROCs). TCWB1T also has the same level of skill scores as NCEP CFSv2 and/or the ECMWF fifth-generation seasonal forecast system (SEAS5), based on EOF, anomaly pattern correlation, climatological bias, RMSE, temporal correlation, and anomaly correlation percentage of forecast skill. TCWB1T shows forecast skill that is better in winter than in summer. Overall, it indicates that TCWB1T can be used for seasonal ENSO predictions.

Using Calibrated Rainfall Forecasts and Observed Rainfall to Produce Probabilistic Meteorological Drought Forecasts

Most existing drought forecast systems rely only on observed or forecast rainfall, losing valuable context gained from considering both. The lack of a direct link between observed and forecast rainfall reduces the physical consistency of a system, motivating the development of a methodology that can directly link the two. The methodology developed in this study allows the comparison of the calibrated ensemble forecasts of rainfall totals from a dynamical climate model to observed rainfall deficiencies from a gridded rainfall analysis. The methodology is used to create a probabilistic product that forecasts the chance of entering meteorological drought, with lead times of one month (monthly forecast) and three months (seasonal forecast). Existing deficiency areas are included to facilitate analysis of how these areas are forecast to change. The performance of the developed methodology was verified using Percent Correct (PC), Brier Score (BS), and Relative Operating Characteristic (ROC) statistics. Analysis of the forecast plots was also completed visually. Forecast performance for areas with existing deficiencies as well as for non-deficiency areas was promising (PC rates of >79% and >97%, respectively). Although PC rates for observed deficiencies were low across most months, the mean forecast probability for these areas was 36%, indicating the system had value and outperformed climatology. A calibrated, coupled product like the one scoped in this study has not been explored and we note that it could be an invaluable tool for quantifying meteorological drought onset and persistence in Australia.

Integrating Sigmoid Calibration Function into Entropy Thresholding Segmentation for Enhanced Recognition of Potholes Imaged Using a UAV Multispectral Sensor

This study was aimed at enhancing pothole detection by combining sigmoid calibration function and entropy thresholding segmentation on UAV multispectral imagery. UAV imagery was acquired via the flying of the DJI Matrice 600 (M600) UAV system, with the MicaSense RedEdge imaging sensor mounted on its fixed wing. An endmember spectral pixel denoting pothole feature was selected and used as the base from which spectral radiance patterns of a pothole were analyzed. A field survey was carried out to measure pothole diameters, which were used as the base on which the pothole area was determined. Entropy thresholding segmentation was employed to classify potholes. The sigmoid calibration function was used to reconfigure spectral radiance properties of the UAV spectral bands to pothole features. The descriptive statistics was computed to determine radiance threshold values to be used in demarcating potholes from the reconfigured or calibrated spectral bands. The performance of the sigmoid calibration function was evaluated by analyzing the area under curve (AUC) results generated using the Relative Operating Characteristic (ROC) technique. Spectral radiance pattern analysis of the pothole surface revealed high radiance values in the red channel and low radiance values in the near-infrared (NIR) channels of the spectrum. The sigmoid calibration function radiometrically reconfigured UAV spectral bands based on a total of 500 sampled pixels of pothole surface obtained from all the spectral channels. Upon successful calibration of UAV radiometric properties to pothole surface, the reconfigured mean radiance values for pothole surface were noted to be 0.868, 0.886, 0.944, 0.211 and 0.863 for blue, green, red, NIR and red edge, respectively. The area under curve (AUC) results revealed the r2 values of 0.53, 0.35, 0.71, 0.19 and 0.35 for blue, green, red, NIR and red edge spectral channels, respectively. Overestimation of pothole 1 by both original and calibrated spectral channels was noted and can be attributed to the presence of soils adjacent to the pothole. However, calibrated red channel estimated pothole 2 and pothole 3 accurately, with a slight area deviation from the measured potholes. The results of this study emphasize the significance of reconfiguring radiometric properties of the UAV imagery for improved recognition of potholes.

Relative economic value of global ensemble prediction system of NCMRWF, India, for extreme weather events

AbstractAn ensemble prediction system quantifies the uncertainty in the forecast by a numerical weather prediction model and helps in decision‐making. The global ensemble prediction system (NEPS‐G) of NCMRWF, India, has 1 control and 22 perturbed ensemble members. In the present study, the relative economic value of NEPS‐G forecast has been investigated based on a simple decision‐analytic model. Temperature at 850 hPa (T850), maximum surface temperature (Tmax) and precipitation (rf) over the Indian domain have been studied. Ensemble mean forecast offers a larger value to the users than the control forecast. For rare extreme events, the area under the curve (T‐AUC) of a relative operating characteristic (ROC) obtained using the trapezoidal approximation for 22‐member NEPS‐G (NEPS‐22) is significantly smaller than the area under the curve (Z‐AUC) of the full ROC obtained using binormal model and Z‐transformation. As a result, the discrimination ability and relative economic value of NEPS‐G are underestimated. A method (SUB‐EM) which subdivides the lowest probability category into several subcategories and uses ensemble mean forecast as the secondary decision variable to enhance T‐AUC and improve relative economic value of NEPS‐G has been investigated. Tmax > 45°C and rf > 65 mm·day−1 have been considered as extreme events. The impact of increasing the number of perturbed ensemble members from 22 to 33 (NEPS‐33) by running additional 11 perturbed members from 0000 UTC initial condition has also been investigated and compared with the results obtained using SUB‐EM. SUB‐EM offers larger economic value to the users with small cost–loss ratio (α) without engaging any extra computational resources. An experiment is also carried out to study the impact of using different ensemble summary statistics as a secondary decision variable. Ensemble Maximum provides maximum value and benefits the largest range of users.

Probabilistic skill of statistically downscaled ECMWF S2S forecasts of maximum and minimum temperatures for weeks 1–4 over South Africa

AbstractThe probabilistic forecast skill level of statistically downscaled European Centre for Medium‐Range Weather Forecasts (ECMWF) subseasonal‐to‐seasonal (S2S) forecasts is determined in predicting maximum and minimum temperatures for weeks 1–4 lead times during 20‐year December–January–February (DJF) seasons from 2001 to 2020 over South Africa. Skilful S2S forecasts are vital in assisting decision‐makers in the development of contingency planning for any eventualities that may arise because of weather and climate phenomena. Extreme high‐ and low‐temperature events over a prolonged period can lead to hyperthermia and hypothermia, respectively, and can lead to loss of life. The results from the relative operating characteristic (ROC) and reliability diagrams indicate that the ECMWF S2S model has skill in predicting maximum temperature up to week 3 ahead, particularly over the central and eastern parts of South Africa. The ROC scores indicate that the model has skill in predicting minimum temperature up to week 4 ahead for the above‐normal category, particularly over the central and eastern parts of South Africa. Reliability diagrams indicate that the model has a tendency of overestimating the below‐normal category when predicting both maximum and minimum temperatures for weeks 1–4 lead times over South Africa. Furthermore, canonical correlation analysis (CCA) pattern analysis suggests that when there are anomalously positive and negative predicted 850‐hPa geopotential heights located over South Africa, there are anomalously hot and cold conditions during the DJF seasons over most parts of South Africa, respectively. These results suggests that statistical downscaling of model forecasts can improve forecast skill. Moreover, the results suggest that there is potential for S2S predictions in South Africa, and as such, S2S prediction system for maximum and minimum temperatures can be developed.

LUM as a novel prognostic marker and its correlation with immune infiltration in gastric cancer: a study based on immunohistochemical analysis and bioinformatics

BackgroundGastric cancer (GC) is considered the sixth highly prevailing malignant neoplasm and is ranked third in terms of cancer mortality rates. To enable an early and efficient diagnosis of GC, it is important to detect the fundamental processes involved in the oncogenesis and progression of gastric malignancy. The understanding of molecular signaling pathways can facilitate the development of more effective therapeutic strategies for GC patients.MethodsThe screening of genes that exhibited differential expression in early and advanced GC was performed utilizing the Gene Expression Omnibus databases (GSE3438). Based on this, the protein and protein interaction network was constructed to screen for hub genes. The resulting list of hub genes was evaluated with bioinformatic analysis and selected genes were validated the protein expression by immunohistochemistry (IHC). Finally, a competing endogenous RNA network of GC was constructed.ResultsThe three genes (ITGB1, LUM, and COL5A2) overexpressed in both early and advanced GC were identified for the first time. Their upregulation has been linked with worse overall survival (OS) time in patients with GC. Only LUM was identified as an independent risk factor for OS among GC patients by means of additional analysis. IHC results demonstrated that the expression of LUM protein was increased in GC tissue, and was positively associated with the pathological T stage. LUM expression can effectively differentiate tumorous tissue from normal tissue (area under the curve = 0.743). The area under 1-, 3-, and 5-year survival relative operating characteristics were greater than 0.6. Biological function enrichment analyses suggested that the genes related to LUM expression were involved in extracellular matrix development-related pathways and enriched in several cancer-related pathways. LUM affects the infiltration degree of cells linked to the immune system in the tumor microenvironment. In GC progression, the AC117386.2/hsa-miR-378c/LUM regulatory axis was also identified.ConclusionCollectively, a thorough bioinformatics analysis was carried out and an AC117386.2/hsa-miR-378c/LUM regulatory axis in the stomach adenocarcinoma dataset was detected. These findings should serve as a guide for future experimental investigations and warrant confirmation from larger studies.

Adaptive selection of members for convective-permitting regional ensemble prediction over the western Maritime Continent

A common issue faced by the downscaled regional ensemble prediction systems is the under-dispersiveness of the ensemble forecasts, often attributed to the lack of spread under the initial conditions from the global ensemble. In this study, a novel method that adopts an adaptive approach to selecting global ensemble members for regional downscaling has been developed. Instead of using a fixed set of pre-selected global ensemble members, the adaptive selection performs a sampling algorithm and selects the global ensemble members, which maximizes a fractions skill score (FSS)-based displacement between ensemble members. The method is applied to a convective-permitting ensemble prediction system over the western Maritime Continent, referred to as SINGV-EPS. SINGV-EPS has a grid spacing of 4.5 km and is a 12-member ensemble that is driven by the European Centre for Medium-Range Weather Forecasts (ECMWF) 51-member global ensemble. Month-long trials were conducted in June 2020 to assess the impact of adaptive selection on the ensemble forecast spread and rainfall verification scores. In both fixed pre-selection and adaptive selection experiments, SINGV-EPS was still under-dispersive. However, adaptive selection improved the ensemble spread and reduced the root-mean-square error (RMSE) of the ensemble mean in wind, temperature, and precipitation fields. Further verification of the rainfall forecasts showed that there was a reduction in the Brier score and a higher hit rate in the relative operating characteristic (ROC) curve for all rainfall thresholds when adaptive selection was applied. Additionally, the ensemble mean forecasts from adaptive selection experiments are more accurate beyond 24 h, with a higher FSS for all rainfall thresholds and neighborhood lengths. These results suggest that the adaptive selection is superior to the fixed pre-selection of global ensemble members for downscaled regional ensemble prediction.

Evaluation of Probabilistic Forecasts of Extreme Cold Events in S2S Models

The probabilistic prediction skill of the weekly forecasts of extreme cold events (ECE) is illustrated and measured in the form of the Brier Skill Score (BSS) and the area under Relative Operating Characteristics (ROC) curves based on the subseasonal-to-seasonal (S2S) prediction project database. The ROC scores show that six S2S models have the good potential predictability skill required for use in ECE probabilistic forecasts, and they were more useful than climatologic probabilistic models in creating forecasts of about 3–4 weeks in length. However, the BSS results show that the actual prediction skill of six models used in ECE probabilistic forecasts are different. The ECMWF model has a good performance, and its actual probabilistic prediction skill of ECE for forecasts of about 3–4 weeks in length was higher than those of climatology, which operates close to its potential predictability. The actual probabilistic prediction skill of the NCEP model for ECE was only about 2 weeks over the extra-tropics, and no skill was recorded over the tropics given its bad reliability, especially over the tropics. BoM, JMA, and CNRM models only have a 1-week actual prediction skill over the Northern Hemisphere extra-tropics, and they have no skill over the rest of the world’s land area. The CNR-ISAC model has a 1-week actual prediction skill over the extra-tropics and about 4 weeks over the tropics. There is still much room for improvement in the prediction ability of models used for ECE. MJO in tropical regions has an important influence on the probabilistic prediction skill of ECE required at middle and high latitudes. When there is an MJO in the initial conditions, the potential predictability and actual prediction skill of ECE probabilistic forecasts over North America in the 3rd week and over Europe in the 3rd–4th weeks are higher than those without MJO.

A novel approach for flood hazard assessment using hybridized ensemble models and feature selection algorithms

Identifying flood-prone regions is critical for effective management of flood hazards as floods are among the most devastating natural disasters globally. However, accurate modeling and prediction of floods are challenging due to their complexity. The current research has proposed a novel approach for Flood Hazard (FH) prediction using hybrid Machine Learning (ML) models that integrate ensemble ML models with several Feature Selection (FS) algorithms. An optimum set of Flood Influential Factors (FIFs) was determined using the Simulated Annealing (SA) and Information Gain (IG) FS algorithms. The ensemble ML models employed include AdaboostM1 (ABM), Boosted Generalized Linear Model (BGLM), and Stochastic Gradient Boosting (SGB) algorithms. In addition, the hyper-parameters of the hybrid models were optimized using the random search (RS) method and repeated cross-validation technique. The proposed hybrid models were trained using flood inventory map and FIFs obtained from a spatial database. The results verified that the SA and IG algorithms detect 9 and 13 factors as FIFs in the FH assessment, respectively. Moreover, rainfall, distance to river, altitude, and lithology FIFs have a greater impact than the other factors in the Sardabroud watershed, Mazandaran Province, Iran. Several robust indicators, such as the area under curve (AUC) in relative operating characteristic (ROC) curves and statistical measurements, were employed to assess the robustness of hybrid models. SA-ABM model had the highest AUC value (0.983), while IG-ABM, SA-BGLM, SA-SGB, IG-BGLM, and IG-SGB had lower values (0.952 to 0.973). Finally, the SA-ABM hybrid model classified 27% of the study area as having a high hazard of floods.

Probabilistic vs deterministic forecasts – interpreting skill statistics for the benefit of users

Owing to probabilistic uncertainties associated with seasonal forecasts, especially over areas such as southern Africa where forecast skill is limited, non-climatologists and users of such forecasts frequently prefer them to be presented or distributed in terms of the likelihood (expressed as a probability) of certain categories occurring or thresholds being exceeded. Probabilistic forecast verification is needed to verify such forecasts. Whilst the resulting verification statistics can provide clear insights into forecast attributes, they are often difficult to understand, which might hinder forecast uptake and use. This problem can be addressed by issuing forecasts with some understandable evidence of skill, with the purpose of reflecting how similar forecasts may have performed in the past. In this paper, we present a range of different probabilistic forecast verification scores, and determine if these statistics can be readily compared to more commonly known and understood ‘ordinary’ correlations between forecasts and their associated observations – assuming that ordinary correlations are more intuitively understood and informative to seasonal forecast users. Of the range of scores considered, the relative operating characteristics (ROC) was found to be the most intrinsically similar to correlation.

Utility of the Brief Young Adult Alcohol Consequences Questionnaire to Identify College Students At-Risk for Alcohol Related Problems: Relative Operating Characteristics across Seven Countries

Background: It is important to identify students who would benefit from early interventions to reduce harmful drinking patterns and associated consequences. the Brief Young Adult Alcohol Consequences Questionnaire (B-YAACQ) could be particularly useful as a screening tool in university settings. Objectives. The present study examined the utility of the B-YAACQ to distinguish among students at-risk for problematic alcohol use as measured by the AUDIT. Objectives: The present study examined the utility of the B-YAACQ to distinguish among students at-risk for problematic alcohol use as measured by the AUDIT. Methods: A sample of 6382 students (mean age=20.28, SD=3.75, 72.2% females) from seven countries (i.e., U.S., Canada, South-Africa, Spain, Argentina, Uruguay, England) completed the B-YAACQ, the AUDIT and different measures of alcohol use. Results: ROC analyses suggested that a cutoff score of 5 maximized the YAACQ’s discrimination utility to differentiate between students at low versus moderate/high risk in the total sample and across countries (except in Canada, where the cutoff was 4). In addition, a cutoff of 7 differentiated between students at low/moderate versus high risk in the total sample, while cutoffs of 10, 9, 8 and 7 differentiate between students at low/moderate versus high risk in Uruguay, U.S and Spain (10), Argentina (9), England (8), and Canada and South-Africa (7), respectively. Students classified at the three risk levels (i.e., low, moderate and high) differed in age (i.e., a younger age was associated with higher risk) and drinking patters (i.e., higher drinking frequency, quantity, binge drinking and AUDIT and B-YAACQ scores in the higher risk groups). Conclusions: This study suggest that the B-YAACQ is a useful tool to identify college students at-risk for experiencing problematic patterns of alcohol use.

FOREST FIRE SUSCEPTIBILITY MAPPING OF BHUTAN USING LOGISTIC REGRESSION AND FREQUENCY RATIO MODEL

Forest fire is not only observed as one of the most significant sources of forest degradation in Bhutan but also a serious danger to national conservation efforts. As a result, forest fire susceptibility analysis is recognised as an important part of Bhutan's forest fire management strategy. The study's major goal is to create a forest fire susceptibility map for Bhutan using logistic regression (LR) and frequency ratio (FR) models. The study gathered number of fire influencing factors, evaluated them, and created susceptibility maps. Using the relative operating characteristics technique, the efficiency of each of the two models was analysed and compared to select the best model. The Receiver Operating Characteristics (ROC) curves with the area under the curve (AUC) was used to check the correctness of the maps produced by the modelling procedure. The prediction and success rates of the LR model were 88.8% and 87.5%, while for the FR model they were 85.4% and 85.1%, respectively. The results showed that both models are good predictors of forest fire with the LR model performing fairly better than the FR model. So, the LR model was chosen as an optimum model for forest fire susceptibility mapping. The susceptibility map obtained from the optimum LR model was classified into five categories such as; very low, low, moderate, high, and very high.. The findings of this study give useful spatial information for implementing forest management techniques.

Clinical significance of prognostic nutritional index (PNI)-monocyte-to-lymphocyte ratio (MLR)-platelet (PLT) score on postoperative outcomes in non-metastatic clear cell renal cell carcinoma

BackgroundPrognositic nutritional index (PNI), monocyte-to-lymphocyte ratio (MLR) and platelet (PLT) are associated with tumor survival in many human malignancies. Whereas, no study combined PNI-MLR-PLT score and indicated its predictive significance on the prognosis of patients with non-metastatic clear cell renal cell carcinoma (ccRCC).MethodsIn this study, we retrospectively collected the clinicopathological characteristics and prognostic data from 164 cases of non-metastatic ccRCC and aimed to determine the clinical significance of PNI-MLR-PLT score on patients’ outcomes after surgery. The optimal cut-off values of PNI (PNI > 47.40 vs PNI < 47.40), MLR (MLR > 0.31 vs MLR < 0.31) and PLT (PLT > 245 vs PLT < 245) were identified with relative operating characteristic (ROC) curve analysis. The PNI-MLR-PLT score system was established by the value of three indexes, each indication was assigned a score of 0 or 1. Overall survival (OS) and metastasis-free survival (MFS) were analyzed using Kaplan–Meier estimate and Cox regression models.ResultsThe mean follow-up period was 85.67 months. Eight (5.0%) patients died, 4 (2.0%) relapsed, and 7 (4.0%) developed metastasis after surgery. The 3-year OS and MFS rates were 98.2% and 97.6%, and the 5-year OS and MFS rates were both 90.2%. Our results suggested that PNI-MLR-PLT score negatively correlated with pathological T stage and tumor grade. Survival outcomes revealed that lower PNI-MLR-PLT score is associated with inferior OS (P < 0.001) and MFS (P < 0.001) after surgery. Subgroup analysis regarding pathological T stage, tumor grade and surgical modalities obtained consistent results. univariable and multivariable Cox analysis showed that high PNI-MLR-PLT score was the independent protective factor of tumor survival in non-metastatic ccRCC patients.ConclusionsOur data suggested that PNI-MLR-PLT score could serve as a promising independent prognostic factor in patients with non-metastatic ccRCC.

How to assess severe burnout? Cutoff points for the Burnout Assessment Tool (BAT) based on three European samples

Despite decades of burnout research, clinical validated cut-off scores that discriminate between those who suffer from burnout and those who don't are still lacking. To establish such cut-off scores, the current study uses a newly developed questionnaire, the Burnout Assessment Tool (BAT) that consists of four subscales (exhaustion, mental distancing, and emotional and cognitive impairment). Separate cut-offs were computed for those at risk for burnout and those suffering from severe burnout for the original BAT-23 as well as for the shortened BAT-12. Relative operating characteristic (ROC) analyses were carried out using representative samples of healthy employees from The Netherlands (N=1370), Belgium (Flanders; N=1403) and Finland (N=1350). In addition, samples of employees who received a burnout diagnosis were used (N=335, 158 and 50, respectively). The diagnostic accuracy of the BAT (area under the curve) ranges from good to excellent with the exception of mental distancing, which is fair. The country-specific cut-off values as well as their specificity and sensitivity are comparable to those of the pooled sample. In addition to country-specific cut-offs, general cut-offs can be used tentatively in other similar countries, pending future replication studies. Caution is warranted for using cut-offs for mental distance as the sensitivity and specificity of this subscale is relatively poor. It is concluded that the BAT can be used in organizational surveys for identifying employees at risk for burnout and, in clinical treatment settings, for identifying those with severe burnout, keeping in mind the tentativeness of the present cut-offs.

Diagnosis values of three-dimensional power Doppler ultrasonography in polycystic ovary syndrome and its relationship with serum sex hormone levels

BackgroundThe diagnosis of polycystic ovary syndrome (PCOS) is of great significance for early detection, timely standardized treatment and prevention of long-term complications. This study aimed to observe and measure the intraovarian blood flow distribution and blood flow indexes in patients with PCOS by three-dimensional power Doppler ultrasonography, and to evaluate its diagnostic value for PCOS and its correlation with serum sex hormone levels. Experimental designPatients who were diagnosed with PCOS and met the inclusion and exclusion criteria were recruited as the PCOS group, and 85 age-matched healthy women were arranged in healthy control (HC) group. Participants underwent three-dimensional power Doppler ultrasound. Serum sex hormone was analyzed by chemiluminescence. The diagnostic value was analyzed by relative operating characteristic (ROC) analysis. Spearman correlation coefficient analysis was applied to determine the correlation of vascularization index with serum sex hormone levels. ResultsThe vascularization index (VI), flow index (FI), and vascularization flow index (VFI) values in PCOS patients were all statistically higher than those of HC. The combined index (0.445 * VI + 0.1 * FI + 1.057 * VFI) has a higher diagnostic value of PCOS compared with the three indexes alone. ConclusionThree-dimensional power Doppler ultrasound could observe and quantitatively evaluate the distribution of blood flow in the ovary, which has a high diagnostic value and might provide a reference in clinical use.

Forecasting land use and land cover dynamics using combined remote sensing, machine learning algorithm and local perception in the Agoènyivé Plateau, Togo

Knowledge of land use and land cover (LULC) dynamics helps policymakers set sustainable land management plans. Population growth, migration, and rural exodus have led to spatial expansion in many cities worldwide, especially in coastal urban settings. This research aims at assessing and predicting LULC over the Agoènyivé plateau (AP) in Togo, using remote sensing and Markov Chain along with local perceptions on LULC change, thus considering four scenarios (i.e., Business-as Usual, afforestation, wetland policy, and building policy). LULC was classified based on the maximum likelihood algorithm using Landsat images. The future scenarios maps were produced using the Multilayer Perceptron (MLP) neural networks-Markov chain modelling approach by considering five driver variables considered to affect future development. The historical change analysis was performed for the periods of 1986–2001, 2001–2011, and 2011–2020, while 1986–2020 was used for model validation and change prediction. Image accuracy assessment was performed using the error or confusion matrices, kappa coefficients (Kscores), Relative Operating Characteristics (ROC), and accuracy scores, with an overall accuracy (Kappa coefficient) of 87% (0.81), 88% (0.81), 90% (0.82), and 92% (0.84) for the years 1986, 2001, 2011, and 2020, respectively. The results showed an increase in built-up areas (38.71% land gain), while a decrease was observed in mixed vegetation/savannah (22.69% land loss), croplands/bare surfaces (22.89%), and wetlands (3.36% land loss) over the period of 1986–2020. An increase in built-up areas (7.79% and 19.79% land gain by 2030 and 2050, respectively) and a decrease in mixed vegetation (1.13% and 2.54% land loss by 2030 and 2050, respectively), croplands and bare surfaces (6.58% and 16.98% loss by 2030 and 2050, respectively), and wetlands (0.13% and 0.31% loss by 2030 and 2050, respectively), are expected under the BAU scenario. Contrary to the wetland policy, which induces change only in the wetlands (0.02% and 0.047% land loss by 2030 and 2050, respectively), the afforestation scenario results in a gain in forest/savannah (0.11% and 0.73% land gain by 2030 and 2050 compared to the BAU scenario), but also a decrease in croplands/bare surfaces (0.64% by 2050 compared to the BAU scenario), whereas the building policy scenario results in a long-term increase in croplands/bare surfaces (2.88% by 2050, compared to the BAU), and wetlands (0.027 and 2.88% by 2050) in addition to the mixed vegetation/savannah. LULC dynamics (including future urbanization trends) for the AP under various scenarios is a step ahead of time, highlighting the importance of the implementation of existing laws and policies, but also providing information to deal with the observed inharmonious spatial development of urban centres, and serving as a dataset source for LULC change impact assessments on related resources.

Seasonal forecasting of snow resources at Alpine sites

Abstract. Climate warming in mountain regions is resulting in glacier shrinking, seasonal snow cover reduction, and changes in the amount and seasonality of meltwater runoff, with consequences on water availability. Droughts are expected to become more severe in the future with economical and environmental losses both locally and downstream. Effective adaptation strategies involve multiple timescales, and seasonal forecasts can help in the optimization of the available snow and water resources with a lead time of several months. We developed a prototype to generate seasonal forecasts of snow depth and snow water equivalent with a starting date of 1 November and a lead time of 7 months, so up to 31 May of the following year. The prototype has been co-designed with end users in the field of water management, hydropower production and mountain ski tourism, meeting their needs in terms of indicators, time resolution of the forecasts and visualization of the forecast outputs. In this paper we present the modelling chain, based on the seasonal forecasts of the ECMWF and Météo-France seasonal prediction systems, made available through the Copernicus Climate Change Service (C3S) Climate Data Store. Seasonal forecasts of precipitation, near-surface air temperature, radiative fluxes, wind and relative humidity are bias-corrected and downscaled to three sites in the Western Italian Alps and finally used as input for the physically based multi-layer snow model SNOWPACK. Precipitation is bias-corrected with a quantile mapping method using ERA5 reanalysis as a reference and then downscaled with the RainFARM stochastic procedure in order to allow an estimate of uncertainties due to the downscaling method. The impacts of precipitation bias adjustment and downscaling on the forecast skill have been investigated. The skill of the prototype in predicting the deviation of monthly snow depth with respect to the normal conditions from November to May in each season of the hindcast period 1995–2015 is demonstrated using both deterministic and probabilistic metrics. Forecast skills are determined with respect to a simple forecasting method based on the climatology, and station measurements are used as reference data. The prototype shows good skills at predicting the tercile category, i.e. snow depth below and above normal, in the winter (lead times: 2–3–4 months) and spring (lead times: 5–6–7 months) ahead: snow depth is predicted with higher accuracy (Brier skill score) and higher discrimination (area under the relative operating characteristics (ROC) curve skill score) with respect to a simple forecasting method based on the climatology. Ensemble mean monthly snow depth forecasts are significantly correlated with observations not only at short lead times of 1 and 2 months (November and December) but also at lead times of 5 and 6 months (March and April) when employing the ECMWFS5 forcing. Moreover the prototype shows skill at predicting extremely dry seasons, i.e. seasons with snow depth below the 10th percentile, while skills at predicting snow depth above the 90th percentile are model-, station- and score-dependent. The bias correction of precipitation forecasts is essential in the case of large biases in the global seasonal forecast system (MFS6) to reconstruct a realistic snow depth climatology; however, no remarkable differences are found among the skill scores when the precipitation input is bias-corrected, downscaled, or bias-corrected and downscaled, compared to the case in which raw data are employed, suggesting that skill scores are weakly sensitive to the treatment of the precipitation input.

Deep Learning Algorithm for Detection of Protein Remote Homology

The study aims to find a successful solution by using computer algorithms to detect remote homologous proteins, which is a significant problem in the bioinformatics field. In this experimental study, structural classification of proteins (SCOP) 1.53, SCOP benchmark, and the newly created SCOP protein database from the structural classification of proteins—extended (SCOPe) 2.07 were used to detect remote homolog proteins. N-gram method and then Term Frequency-Inverse Document Frequency (TF-IDF) weighting were performed to extract features of the protein sequences taken from these databases. Next, a smoothing process on the obtained features was performed to avoid misclassification. Finally, the proteins with balanced features were classified into remote homologs using the built deep learning architecture. As a result, remote homologous proteins have been detected with novel deep learning architecture using both negative and positive protein instances with a mean accuracy of 89.13% and a mean relative operating characteristic (ROC) score of 88.39%. This experiment demonstrated the following: 1) The successful outcome of this study in detecting remote homology is auspicious in discovering new proteins and thus in drug discovery in medicine. 2) Natural language processing (NLP) techniques were used successfully in bioinformatics, 3) the importance of choosing the correct n-value in the n-gram process, 4) the necessity of using not only positive but negative instances in a classification problem, and 5) how effective the processes, such as smoothing, are in the classification accuracy in an imbalanced dataset. 6) The deep learning architecture gives better results than the support vector machine (SVM) model on the smoothed data to detect proteins’ remote homology.

Combining short-range dispersion simulations with fine-scale meteorological ensembles: probabilistic indicators and evaluation during a 85Kr field campaign

Abstract. Numerical atmospheric dispersion models (ADMs) are used for predicting the health and environmental consequences of nuclear accidents in order to anticipate countermeasures necessary to protect the populations. However, these simulations suffer from significant uncertainties, arising in particular from input data: weather conditions and source term. Meteorological ensembles are already used operationally to characterize uncertainties in weather predictions. Combined with dispersion models, these ensembles produce different scenarios of radionuclide dispersion, called “members”, representative of the variety of possible forecasts. In this study, the fine-scale operational weather ensemble AROME-EPS (Applications of Research to Operations at Mesoscale-Ensemble Prediction System) from Météo-France is coupled with the Gaussian puff model pX developed by the IRSN (French Institute for Radiation Protection and Nuclear Safety). The source term data are provided at 10 min resolution by the Orano La Hague reprocessing plant (RP) that regularly discharges 85Kr during the spent nuclear fuel reprocessing process. In addition, a continuous measurement campaign of 85Kr air concentration was recently conducted by the Laboratory of Radioecology in Cherbourg (LRC) of the IRSN, within 20 km of the RP in the North-Cotentin peninsula, and is used for model evaluation. This paper presents a probabilistic approach to study the meteorological uncertainties in dispersion simulations at local and medium distances (2–20 km). First, the quality of AROME-EPS forecasts is confirmed by comparison with observations from both Météo-France and the IRSN. Then, the probabilistic performance of the atmospheric dispersion simulations was evaluated by comparison to the 85Kr measurements carried out during a period of 2 months, using two probabilistic scores: relative operating characteristic (ROC) curves and Peirce skill score (PSS). The sensitivity of dispersion results to the method used for the calculation of atmospheric stability and associated Gaussian dispersion standard deviations is also discussed. A desirable feature for a model used in emergency response is the ability to correctly predict exceedance of a given value (for instance, a dose guide level). When using an ensemble of simulations, the “decision threshold” is the number of members predicting an event above which this event should be considered probable. In the case of the 16-member dispersion ensemble used here, the optimal decision threshold was found to be 3 members, above which the ensemble better predicts the observed peaks than the deterministic simulation. These results highlight the added value of ensemble forecasts compared to a single deterministic one and their potential interest in the decision process during crisis situations.

Urban growth modeling based on cellular automata with transition rules optimized using genetic fuzzy systems

AbstractThis article presents a new methodology for urban growth modeling by integrating cellular automata (CA) and genetic fuzzy algorithms. The urban growth phenomenon is a spatio‐temporal and continuous process that can be modeled by employing fuzzy logic as a framework for handling vagueness. Dependence upon an expert for assigning membership functions and rule weights has made the fuzzy logic approach rather subjective. Our proposed methodology overcomes this shortcoming by applying genetic algorithms to tune and optimize the fuzzy logic system and to make it expert independent. The optimization process encompasses a fuzzy membership function and weights for fuzzy rules. This model uses linguistic variables for defining CA transition rules and applies them to represent the non‐deterministic nature of urban growth. The proposed model is applied to simulate urban growth in the Tehran Metropolitan Area in Iran across time steps of 1988, 1999, and 2010 developed using Landsat TM and ETM+ images and a Digital Elevation Model. The first data pairs were employed for calibration of the model parameters, and the remainder of the data was used for validation of the model across time. The model was evaluated using a relative operating characteristic of 0.88 and a figure of merit statistic of 0.31, which quantifies the model goodness of fit.