{"component": "clause", "props": {"groups": [{"snippet_links": [{"key": "cooperate-with", "type": "clause", "offset": [18, 32]}, {"key": "the-company-and-the", "type": "clause", "offset": [33, 52]}, {"key": "to-validate", "type": "definition", "offset": [89, 100]}, {"key": "by-the-manager", "type": "clause", "offset": [160, 174]}, {"key": "services-under-this-agreement", "type": "clause", "offset": [197, 226]}, {"key": "related-to", "type": "clause", "offset": [277, 287]}, {"key": "the-model", "type": "clause", "offset": [288, 297]}, {"key": "likely-to-have", "type": "clause", "offset": [333, 347]}, {"key": "material-adverse-effect-on-the-company", "type": "definition", "offset": [350, 388]}, {"key": "financial-loss", "type": "clause", "offset": [414, 428]}, {"key": "significant-error", "type": "clause", "offset": [432, 449]}, {"key": "cash-flows", "type": "definition", "offset": [482, 492]}, {"key": "discount-rates", "type": "clause", "offset": [494, 508]}, {"key": "relating-to", "type": "definition", "offset": [536, 547]}, {"key": "violation-of-applicable-law", "type": "clause", "offset": [639, 666]}, {"key": "section-85", "type": "clause", "offset": [719, 730]}, {"key": "as-of-the-effective-date", "type": "clause", "offset": [732, 756]}, {"key": "the-performance", "type": "clause", "offset": [827, 842]}, {"key": "based-on", "type": "clause", "offset": [864, 872]}, {"key": "interest-rate", "type": "clause", "offset": [901, 914]}, {"key": "yield-curve", "type": "definition", "offset": [928, 939]}, {"key": "floating-rate", "type": "definition", "offset": [1021, 1034]}, {"key": "reporting-and-analytics", "type": "clause", "offset": [1087, 1110]}, {"key": "section-91", "type": "definition", "offset": [1139, 1150]}, {"key": "as-agreed", "type": "clause", "offset": [1152, 1161]}], "samples": [{"hash": "jFYiUdaQCnB", "uri": "/contracts/jFYiUdaQCnB#model-validation", "label": "Investment Management Agreement", "score": 32.0151671425, "published": true}, {"hash": "f55kKGdF2FB", "uri": "/contracts/f55kKGdF2FB#model-validation", "label": "Investment Management Agreement", "score": 31.8043898388, "published": true}, {"hash": "1QEIYmE3ZBv", "uri": "/contracts/1QEIYmE3ZBv#model-validation", "label": "Investment Management Agreement", "score": 26.5811088296, "published": true}], "size": 4, "snippet": "The Manager shall cooperate with the Company and the FRBNY in the manner set forth below to validate the conceptual soundness and implementation of models used by the Manager in its performance of services under this Agreement if such model is used in such a way that an error related to the model\u2019s formulation or implementation is likely to have a material adverse effect on the Company, including a significant financial loss, a significant error of analytical outputs including cash flows, discount rates, valuations, or statistics relating to those outputs (such as expected values, variances, percentiles, or stress estimates), or a violation of applicable law or (each, a \u201cMaterial Model\u201d). For purposes of this Section 8.5, as of the Effective Date, the Manager has identified as \u201cMaterial Models\u201d those models used in the performance of services that are based on BlackRock Solutions Aladdin interest rate modeling and yield curve construction techniques utilized for the generation of cash flows, projection of floating rate coupons, and discounting, in support of the regular reporting and analytics to be delivered pursuant to Section 9.1, as agreed upon with FRBNY, including the Manager\u2019s Shifted Lognormal", "hash": "7eb7a1af2c3ee7b7d81e417cc10cf8de", "id": 1}, {"snippet_links": [{"key": "relating-to", "type": "definition", "offset": [178, 189]}, {"key": "gold-standard", "type": "definition", "offset": [342, 355]}, {"key": "best-fit", "type": "definition", "offset": [385, 393]}, {"key": "in-relation-to", "type": "clause", "offset": [438, 452]}, {"key": "a-\u2587", "type": "clause", "offset": [799, 802]}, {"key": "term-was", "type": "clause", "offset": [874, 882]}], "samples": [{"hash": "5Dte2twvXLu", "uri": "/contracts/5Dte2twvXLu#model-validation", "label": "End User License Agreement", "score": 21.923340178, "published": true}], "size": 2, "snippet": "Multiple regression analyses (\u2587\u2587\u2587\u2587\u2587\u2587 et al., 1995, \u2587\u2587\u2587\u2587\u2587\u2587\u2587 et al., 2002, \u2587\u2587\u2587\u2587 et al., 2007) and indices of adiposity were assessed (\u2587\u2587\u2587\u2587\u2587\u2587 et al., 2000) to address two questions relating to the estimation of total abdominal visceral fat using DXA adiposity and a range of anthropometric measures: 1) which of these predictive models for the \u201cgold standard\u201d CT measure of visceral fat, best fit our validation sample of 54 females; and 2) in relation to previous discussions (\u2587\u2587\u2587\u2587\u2587\u2587 et al., 2000), can visceral fat be reliably estimated based upon anthropometry alone. CT and DXA scans for the same individuals were date-matched to between 0.23 - 2.5 years of one another. The difference in scan date for the validation sample was included in all visceral fat regression models as a nuisance factor. A \u2587\u2587\u2587\u2587\u2587-\u2587\u2587\u2587\u2587\u2587\u2587 analysis was conducted to assess if the predicted VAT error term was constant or varied across the range of CT-measured VAT area.", "hash": "635ce157278cbe874cb74d2f20e0c4c1", "id": 3}, {"snippet_links": [{"key": "the-studies", "type": "clause", "offset": [87, 98]}, {"key": "the-data", "type": "clause", "offset": [153, 161]}, {"key": "training-data", "type": "definition", "offset": [288, 301]}, {"key": "based-on", "type": "clause", "offset": [312, 320]}, {"key": "test-data", "type": "definition", "offset": [344, 353]}, {"key": "the-performance", "type": "clause", "offset": [473, 488]}, {"key": "the-model", "type": "clause", "offset": [492, 501]}, {"key": "new-patients", "type": "clause", "offset": [605, 617]}, {"key": "external-validation", "type": "definition", "offset": [702, 721]}, {"key": "the-original", "type": "definition", "offset": [731, 743]}, {"key": "in-detail", "type": "clause", "offset": [1261, 1270]}, {"key": "in-case-of", "type": "clause", "offset": [1297, 1307]}, {"key": "complex-procedures", "type": "definition", "offset": [1308, 1326]}, {"key": "validation-procedures", "type": "clause", "offset": [1366, 1387]}, {"key": "performance-measures", "type": "clause", "offset": [1571, 1591]}, {"key": "the-c", "type": "clause", "offset": [1678, 1683]}, {"key": "screening-process", "type": "clause", "offset": [1813, 1830]}, {"key": "and-development", "type": "clause", "offset": [2307, 2322]}, {"key": "take-into-account", "type": "definition", "offset": [2408, 2425]}, {"key": "simulation-study", "type": "clause", "offset": [2682, 2698]}, {"key": "model-development", "type": "clause", "offset": [3027, 3044]}, {"key": "event-data", "type": "definition", "offset": [3071, 3081]}, {"key": "the-book", "type": "clause", "offset": [3087, 3095]}, {"key": "reporting-of", "type": "clause", "offset": [3132, 3144]}, {"key": "a-non", "type": "clause", "offset": [3470, 3475]}, {"key": "method-of", "type": "definition", "offset": [3556, 3565]}, {"key": "development-of", "type": "clause", "offset": [3637, 3651]}, {"key": "accuracy-of-the", "type": "clause", "offset": [3787, 3802]}, {"key": "agreement-between", "type": "clause", "offset": [3890, 3907]}, {"key": "not-assessed", "type": "definition", "offset": [4308, 4320]}, {"key": "the-\u2587", "type": "clause", "offset": [4376, 4381]}, {"key": "in-accordance-with", "type": "definition", "offset": [4445, 4463]}, {"key": "in-calibration", "type": "definition", "offset": [4563, 4577]}, {"key": "performance-criterion", "type": "definition", "offset": [4706, 4727]}, {"key": "absolute-error", "type": "definition", "offset": [4994, 5008]}, {"key": "test-1", "type": "definition", "offset": [5034, 5040]}, {"key": "risk-group", "type": "definition", "offset": [5093, 5103]}], "samples": [{"hash": "6SHgcFjrN15", "uri": "/contracts/6SHgcFjrN15#model-validation", "label": "Analysis of Sarcoma and Non Sarcoma Clinical Data With Statistical Methods and Machine Learning Techniques", "score": 25.4366872005, "published": true}], "size": 2, "snippet": "We examined the validation approach for each of the 34 outcomes (clinical endpoints of the studies). Single random split was used 17 times (50.0%), with the data split into single train-test or train-validation-test parts. When the data are split into train-test parts the best model for training data is chosen based on model\u2019s performance on test data, whereas when the data are split into train-validation-test sets the best model for training data is selected based on the performance of the model on validation data. Then the test data are used to internally validate the performance of the model on new patients. Resampling (cross-validation or nested cross-validation) was used 9 times (26.5%). External validation (testing the original prediction model in a set of new patients from a different year, location, country etc.) was used 4 times (11.8%). External validation involved the chronological split of data into training and test parts 3 times (temporal validation), and validation of a new dataset 1 time. Multiple random split was used 2 times (5.9%), with the data split into train-test or train-validation-test data multiple times. Validation was not performed for 2 datasets (5.9%). We recommend reporting the steps of the validation approach in detail, to avoid misconceptions. In case of complex procedures, a comprehensive representation of the validation procedures can be insightful. Researchers should aim at performing both internal and external validations, if possible, to maximize the reliability of the prediction models. Table 5.3 shows the performance measures used for model validation in the 24 studies. A popular measure in the survival field, the C-index, was employed in 8 studies (33.3%, as C-index or time-dependent C-index) and AUC in 5 studies (20.8%). Notably, during the screening process, several manuscripts were identified where AUC and C-statistic were used interchangeably. While there is a link between the dynamic time-dependent AUC and the C-index (the AUC can be interpreted as a concordance index employed to assess model discrimination) [55], the two are not identical and some caution is required. Apart from the C-index, there was no other established measure in the 24 studies (large variability). This issue is of paramount importance as validation (and development) of the SNNs depends on a suitable performance measure. Any candidate measure should take into account the censoring mechanism. By employing performance measures that are commonly used in traditional classification ANNs, such as accuracy, some SNNs were suboptimally validated. Consistency in the use of performance measures should also be considered. In the simulation study of \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587 et al. in 2013 [43], hyperparameter values for PLANN were based on the Bayesian Information Criterion (BIC), while validation of the SNN performance on the test data was performed using the Mean Squared Error (MSE), and the comparison with Cox model was based on the C-index. Proper measures should be employed for model development and validation of time-to-event data (see the book of van Houwelingen and Putter [5]). Reporting of confidence intervals for the predictive measures was examined\u037e 13 studies (54.2%) did not provide confidence intervals. Repeated data resampling was practiced in 6 studies (25.0%). The following remaining approaches were observed: repeating the simulations 500 times\u037e rerunning the SNN 10 times for each covariate\u037e and using a non-parametric confidence interval based on Gaussian approximation (4.2% each). The method of choice was unclear in 2 studies (8.3%). There is a strong need for the development of methods which reflect the amount of uncertainty of an evaluation criterion. This would provide additional insights into the predictive accuracy of the model. Another important aspect of a prediction model is calibration. It refers to the agreement between observed sur- vival probabilities estimated with \u2587\u2587\u2587\u2587\u2587\u2587-\u2587\u2587\u2587\u2587\u2587\u2019\u2587 methodology and the predicted outcomes. Typically, a plot is produced where the subjects are divided into 10 groups based on the deciles of predicted probabilities. Observed survival probabilities are plotted against predicted. In this review, calibration plots were available for only 11 stud- ies (45.9%). Calibration of the SNNs was not assessed in most studies, and as such a neutral comparison with the \u2587\u2587\u2587 proportional hazards model could not be established. This is in accordance with the findings of \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587 et al. (2019) [56], which pinpoint an urgent need for more attention in calibration of modern ML techniques versus traditional regression methods to achieve a fair model comparison in the classification setting. Performance criterion N (%) C-index 7 (29.2%) AUC 5 (20.8%) log-likelihood 3 (12.5%) Accuracy 2 (8.3%) Global Chi-squared statistic of \u2587\u2587\u2587 regression 2 (8.3%) Brier Score 1 (4.2%) Comparison of predicted probabilities with \u2587\u2587\u2587\u2587\u2587\u2587-\u2587\u2587\u2587\u2587\u2587 1 (4.2%) Integrated Brier Score (IBS) 1 (4.2%) Mean Absolute Error (MAE) 1 (4.2%) \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2019\u2587 test 1 (4.2%) Mean Squared Error (MSE) 1 (4.2%) Prognostic risk group discrimination 1 (4.2%) Sensitivity 1 (4.2%) Separation of cases into good and bad prognosis 1 (4.2%) Specificity 1 (4.2%) Survival curves comparison with log-rank test 1 (4.2%) Time-dependent C-index (Ctd) 1 (4.2%) Wilcoxon test (separation of cases into good and bad prognosis) 1 (4.2%) Table 5.3: The performance measures used for model validation across the 24 studies.", "hash": "ef35b65025e697f2cabbfabd36a4c915", "id": 4}, {"snippet_links": [{"key": "the-independent-engineer", "type": "clause", "offset": [104, 128]}, {"key": "certify-that", "type": "clause", "offset": [135, 147]}, {"key": "the-model", "type": "clause", "offset": [171, 180]}, {"key": "simulated-conditions", "type": "clause", "offset": [187, 207]}, {"key": "the-facility", "type": "definition", "offset": [246, 258]}, {"key": "facility-owner", "type": "definition", "offset": [313, 327]}, {"key": "validity-of-the", "type": "clause", "offset": [419, 434]}, {"key": "all-available-information", "type": "definition", "offset": [479, 504]}, {"key": "observed-behaviour", "type": "clause", "offset": [593, 611]}, {"key": "pv-modules", "type": "clause", "offset": [638, 648]}, {"key": "ceb-system", "type": "definition", "offset": [776, 786]}, {"key": "information-provided", "type": "clause", "offset": [825, 845]}, {"key": "provide-a", "type": "definition", "offset": [937, 946]}, {"key": "the-conditions", "type": "clause", "offset": [1058, 1072]}, {"key": "similar-to", "type": "definition", "offset": [1112, 1122]}, {"key": "short-circuit", "type": "clause", "offset": [1151, 1164]}, {"key": "frequency-and", "type": "definition", "offset": [1206, 1219]}], "samples": [{"hash": "lqFoBkNG3sz", "uri": "/contracts/lqFoBkNG3sz#model-validation", "label": "Interconnection Agreement", "score": 34.0972596607, "published": true}, {"hash": "5pm06OvW0t5", "uri": "/contracts/5pm06OvW0t5#model-validation", "label": "Interconnection Agreement", "score": 34.0972596607, "published": true}], "size": 3, "snippet": "All models provided to CEB for use in dynamic simulations shall be validated against site measurements. The Independent Engineer shall certify that the behaviour shown by the model under simulated conditions is representative of the behaviour of the Facility under equivalent conditions. For validation purposes, Facility Owner shall ensure that appropriate tests are performed and measurements are taken to assess the validity of the dynamic model. Facility Owner shall provide all available information showing how the predicted behaviour of the dynamic model to be verified with the actual observed behaviour of a prototype or similar PV modules/Inverter under laboratory conditions and / or actual observed behaviour of the real Facility as installed and connected to the CEB System. If the on-site measurements or other information provided indicate that the dynamic model is not valid in one or more respects, Facility Owner shall provide a revised model whose behaviour corresponds to the observed on-site behaviour as soon as reasonably practicable. The conditions validated should as far as possible be similar to those of interest, e.g. low short circuit level at Interconnection Boundary, large frequency and voltage excursions, primary resource variations.", "hash": "2c78c9e6b3ffb887bfcda2adf7d85bbd", "id": 2}, {"snippet_links": [{"key": "december-2012", "type": "clause", "offset": [15, 28]}], "samples": [{"hash": "ixBMoOKK6we", "uri": "/contracts/ixBMoOKK6we#model-validation", "label": "Engineering Services Contract", "score": 20.6971678997, "published": true}], "size": 1, "snippet": "\uf0b7 March 2012 \u2013 December 2012: To be performed after hydrology completion with additional validation after hydraulic completion.", "hash": "f5d36a48afdf99419a5bf870ea53c160", "id": 5}, {"snippet_links": [{"key": "missing-data", "type": "definition", "offset": [30, 42]}, {"key": "descriptive-statistics", "type": "clause", "offset": [174, 196]}, {"key": "available-by", "type": "definition", "offset": [227, 239]}, {"key": "measurement-model", "type": "definition", "offset": [253, 270]}, {"key": "similar-to", "type": "definition", "offset": [296, 306]}], "samples": [{"hash": "cpDgTh3674w", "uri": "/contracts/cpDgTh3674w#model-validation", "label": "Distribution Agreement", "score": 19.0, "published": true}], "size": 1, "snippet": "As in the calibration sample, missing data were minimal; a single case was missing one of the indicators of condom use and 17 cases were missing the economic index variable. Descriptive statistics for the validation sample are available by request. The measurement model fit statistics were very similar to those of the calibration sample (CFI = .94, RMSEA=.", "hash": "7654a6c5b389fc4a420bdd3b2070852e", "id": 6}, {"snippet_links": [{"key": "in-order-to", "type": "clause", "offset": [56, 67]}, {"key": "the-model", "type": "clause", "offset": [77, 86]}, {"key": "to-verify", "type": "definition", "offset": [115, 124]}, {"key": "affected-by", "type": "definition", "offset": [239, 250]}, {"key": "referring-to", "type": "definition", "offset": [444, 456]}, {"key": "the-appendix", "type": "clause", "offset": [531, 543]}, {"key": "at-the-end-of-the", "type": "clause", "offset": [544, 561]}], "samples": [{"hash": "eP9CAiCt4Pm", "uri": "/contracts/eP9CAiCt4Pm#model-validation", "label": "Master Thesis", "score": 28.9906175699, "published": true}], "size": 1, "snippet": "Mass transport and heat transfer assumptions were taken in order to simplify the model. Therefore, it is important to verify the validity of these hypothesis to avoid deviation from the reality. The real behaviour of the catalyst\u00b4s bed is affected by mass and heat transfer internal and external limitations. In this section, the validation of the taken assumptions and the validation of the whole modelling are developed. All the calculations referring to the mass and heat transfer internal and external constraints are shown in the Appendix at the end of the thesis.", "hash": "8bbcbefbc5ecbe73491a1af0c197b23d", "id": 7}, {"snippet_links": [{"key": "in-the-event", "type": "clause", "offset": [0, 12]}, {"key": "delivery-of", "type": "clause", "offset": [52, 63]}, {"key": "its-service", "type": "definition", "offset": [64, 75]}, {"key": "consistent-with", "type": "clause", "offset": [116, 131]}, {"key": "by-fiserv", "type": "clause", "offset": [153, 162]}, {"key": "with-regard-to", "type": "clause", "offset": [163, 177]}, {"key": "in-accordance-with", "type": "definition", "offset": [238, 256]}, {"key": "applies-to", "type": "clause", "offset": [300, 310]}, {"key": "a-service-provider", "type": "definition", "offset": [311, 329]}, {"key": "client-shall", "type": "clause", "offset": [331, 343]}, {"key": "responsible-for", "type": "clause", "offset": [351, 366]}, {"key": "financial-institution", "type": "clause", "offset": [452, 473]}, {"key": "to-client", "type": "clause", "offset": [496, 505]}, {"key": "additional-charge", "type": "clause", "offset": [512, 529]}, {"key": "a-copy-of", "type": "clause", "offset": [531, 540]}, {"key": "client-base", "type": "clause", "offset": [618, 629]}, {"key": "reasonable-time", "type": "definition", "offset": [664, 679]}, {"key": "confidential-treatment-requested", "type": "definition", "offset": [703, 735]}], "samples": [{"hash": "bbj9yuBNzbF", "uri": "/contracts/bbj9yuBNzbF#model-validation", "label": "Master Agreement (Fulton Financial Corp)", "score": 27.841889117, "published": true}], "size": 1, "snippet": "In the event that Fiserv deploys a model as part of delivery of its Service which Fiserv agrees requires validation consistent with OCC Bulletin 2011-12 by Fiserv with regard to Fiserv\u2019s use of such model, Fiserv will validate such model in accordance with the guidance in OCC Bulletin 2011-12 as it applies to a service provider. Client shall remain responsible for its own model validation in accordance with OCC Bulletin 2011-12, as it applies to a financial institution. Fiserv shall provide to Client at no additional charge, a copy of its model validation report(s) which are provided by Fiserv generally to its client base at no additional charge, within a reasonable time after its completion. [CONFIDENTIAL TREATMENT REQUESTED].", "hash": "0a5747390dfae203fd2b50304c803ac2", "id": 8}, {"snippet_links": [{"key": "experimental-results", "type": "clause", "offset": [211, 231]}, {"key": "less-than-7", "type": "clause", "offset": [416, 427]}, {"key": "the-context", "type": "clause", "offset": [789, 800]}, {"key": "to-develop", "type": "definition", "offset": [933, 943]}, {"key": "head-injury-criteria", "type": "clause", "offset": [960, 980]}, {"key": "based-on", "type": "clause", "offset": [1077, 1085]}, {"key": "of-the-developer", "type": "clause", "offset": [1102, 1118]}, {"key": "to-provide", "type": "definition", "offset": [1138, 1148]}, {"key": "state-of-the-art", "type": "clause", "offset": [1433, 1449]}], "samples": [{"hash": "guaCVoVW1Bl", "uri": "/contracts/guaCVoVW1Bl#model-validation", "label": "Grant Agreement", "score": 24.3552361396, "published": true}], "size": 1, "snippet": "The SUFEHM developed by \u2587\u2587\u2587\u2587 et al. [35] was validated under RADIOSS code against intracranial pressure data from \u2587\u2587\u2587\u2587\u2587\u2019s experiments. The intracranial response was recorded at 5 locations and compared with the experimental results. A good agreement was found for both impact force and head acceleration curves when compared with experimental data. Also the pressure data at five locations were match very well with less than 7% deviation of peak pressure from experimental peak pressure values. This head model was validated under RADIOSS code against intracranial pressure data of Trosseille et al. [41] experiments. Five tests from \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2019s experiments were replicated and a reasonable agreement was observed between simulation and experimental pressure and acceleration curves. In the context of APROSYS SP5 investigations have been completed to try and determine a suitable state-of- the-art numerical head model with which to develop numerical based head injury criteria and to identify the principle head injury mechanisms. The choice of models evaluated was partly based on the willingness of the developer of each head model to provide predictions of intra- cerebral pressure, skull deformation and rupture and brain skull displacement for six impact conditions, detailed in published PMHS impact tests (\u2587\u2587\u2587\u2587\u2587 et al. [37], \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587 et al. [41], \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587 et al. [58], \u2587\u2587\u2587\u2587\u2587 et al. [32]). SUFEHM model was one of the \u201cstate of the art\u201d model. A comparison of the SUFEHM results under RADIOSS code with the other existing FE head model were published by \u2587\u2587\u2587\u2587 and \u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587\u2587 in 2009 [31].", "hash": "06761977cf0725e099671c9c097177c8", "id": 9}, {"snippet_links": [{"key": "simulation-results", "type": "clause", "offset": [22, 40]}, {"key": "meteorological-stations", "type": "definition", "offset": [92, 115]}, {"key": "suburban-station", "type": "definition", "offset": [154, 170]}, {"key": "table-3", "type": "clause", "offset": [370, 377]}, {"key": "the-stations", "type": "clause", "offset": [399, 411]}, {"key": "city-centre", "type": "definition", "offset": [444, 455]}, {"key": "relative-humidity", "type": "definition", "offset": [953, 970]}], "samples": [{"hash": "la9pRPeiNBQ", "uri": "/contracts/la9pRPeiNBQ#model-validation", "label": "Grant Agreement", "score": 21.1930184805, "published": true}], "size": 1, "snippet": "The validation of the simulation results with the observations is done using data from four meteorological stations: an urban station (DEUSTO), an inland suburban station (BASAURI) and two rural stations, one near the coast (GALEA) and the other (DERIO) in a valley parallel to Bilbao. The observed data are provided by the Basque Meteorological Agency (EUSKALMET), see Table 3 for a description of the stations. Urban Deusto -2.966 43.283 0.6 City centre Suburban - Inland Basauri -2.883 43.243 0.4 Resid. high-dense Rural - Coastal Punta galea -3.033 43.373 0.0 None Rural Inland Derio \u22122.852 43.293 0.0 None Data MEAN Sigma ME MSE RMSE RMSEub a) TEMPERATURE Urban OBS 20.78 2.12 URB 20.02 2.51 -0.77 3.39 1.84 1.68 CTRL 19.80 2.69 -0.98 4.13 2.03 1.78 Coastal OBS 19.80 1.38 URB 18.78 1.24 -1.02 2.10 1.45 1.03 CTRL 18.85 1.23 -0.96 2.01 1.42 1.04 Hinterland OBS 21.17 2.53 URB 19.25 2.80 -1.92 7.57 2.75 1.97 CTRL 19.33 2.95 -1.84 7.19 2.68 1.95 b) RELATIVE HUMIDITY Urban OBS 82.45 6.50 URB 68.47 12.28 -3.98 297.87 17.26 10.11 CTRL 70.76 13.50 -11.69 255.15 15.97 10.88 Coastal OBS 91.71 5.46 URB 81.89 8.78 -9.82 191.74 13.85 9.76 CTRL 77.98 6.40 -13.73 222.20 14.91 5.80 Hinterland OBS 94.17 8.55 URB 73.81 14.29 -20.36 560.77 23.68 12.09 CTRL 73.61 14.99 -20.56 571.01 23.90 12.18 c) WIND Urban OBS 2.31 1.27 URB 1.78 0.96 -0.52 1.55 1.24 1.129 CTRL 1.90 1.43 -0.40 1.80 1.34 1.281 Coastal OBS 3.60 2.21 URB 2.69 1.46 -0.91 4.69 2.16 1.965 CTRL 2.74 1.63 -0.86 4.29 2.07 1.885 Hinterland OBS 1.91 1.37 URB 1.64 1.08 -0.26 1.05 1.02 0.989 CTRL 1.78 1.40 -0.13 0.87 0.93 0.923", "hash": "ac76df8191c05501a7474a8b2795008d", "id": 10}], "next_curs": "ClkSU2oVc35sYXdpbnNpZGVyY29udHJhY3RzcjULEhZDbGF1c2VTbmlwcGV0R3JvdXBfdjU2Ihltb2RlbC12YWxpZGF0aW9uIzAwMDAwMDBhDKIBAmVuGAAgAA==", "clause": {"size": 21, "parents": [["access-to-records-and-documents", "Access to Records and Documents"], ["forecasting", "Forecasting"], ["notice-for-initial-synchronisation", "Notice for Initial Synchronisation"], ["modelling-requirements", "Modelling requirements"], ["analysis-of-bilbaos-urban-climate", "Analysis of Bilbaos Urban Climate"]], "title": "Model Validation", "children": [["london", "London"], ["bilbao", "Bilbao"], ["antwerp", "Antwerp"], ["diffusion-limitations", "Diffusion limitations"], ["heat-transfer-limitations", "Heat transfer limitations"]], "id": "model-validation", "related": [["validation", "Validation", "Validation"], ["validation-mechanism", "Validation Mechanism", "Validation Mechanism"], ["traceability", "Traceability", "Traceability"], ["inspection-and-testing", "Inspection and Testing", "Inspection and Testing"], ["effect-of-completion", "Effect of Completion", "Effect of Completion"]], "related_snippets": [], "updated": "2025-07-07T12:37:48+00:00"}, "json": true, "cursor": ""}}