Modiri, Ehsan · Shrestha, Pallav Kumar · Samaniego Eguiguren, Luis Eduardo

70 files · 34 GB · netcdfdeclared

Historical Hydrological Simulations over the South African Domain (1990-2024) The mHM's simulations of the Planet4Health project This dataset contains historical hydrological simulations for the South African domain (domain 1020011530) conducted with the Mesoscale Hydrological Model (mHM) at a spatial resolution of 0.015625°. The simulation period spans 1990-2024 and was part of the Planet4Health (P4H) project, utilising the ERA5 meteorological forcing. This archive is prepared for DOI assignment and ensures long-term reproducibility. It includes relevant clipped NetCDF components for soil water content layers 3 and 4, consistent with the infrastructure provided within the Helmholtz Centre for Environmental Research (UFZ). The simulations were executed using a specific version of the mHM model with the SCC method for gauges, paired with the mRMv1.0 routing configuration. 🛰️ Simulation Details Model: Mesoscale Hydrological Model (mHM) Codebase: scc_for_gauges branch (https://git.ufz.de/shresthp/mhm/-/tree/scc_for_gauges?ref_type=heads) Spatial resolution: 0.015625° Temporal resolution: Daily Simulation period: 1990-2024 Simulation type: Historical simulation Spin-up: 30-year spin-up using 1990-2019 ERA5 climatology Model version: v1.0 Setup Scope: Model run for domain 1020011530, post-processed and clipped. Configuration & Modules The configuration utilises standard structural components with the SCC methodology. Modules included: Snow processes: Degree-day method Soil moisture: Feddes equation for evapotranspiration reduction Infiltration: Multi-layer Brooks-Corey-like approach Direct runoff: Linear reservoir exceedance method Potential evapotranspiration: Hargreaves-Samani method Interflow: Storage reservoir with nonlinear outflow Groundwater: Linear reservoir Routing: Adaptive time-step routing with mRMv1.0 mechanisms 📥 Input Datasets Meteorological Forcing: ERA5 (Hersbach et al., 2020) at a native input meteorological resolution of 0.25°, dynamically downscaled/mapped to model requirements. Processing Infrastructure: Tracked, processed, and validated under the Planet4Health deployment pipeline (https://git.ufz.de/planet4health/mhm_production/-/tree/main/postproc?ref_type=heads). Data Interfaces: Climate Data Interface version 2.2.4 (CDI) | Climate Data Operators version 2.2.2 (CDO) | NetCDF Operators version 5.1.7 (NCO). 📤 Output Variables swc_l03: Soil water content layer 3 (150-300 mm depth) [mm] swc_l04: Soil water content layer 4 (300-500 mm depth) [mm] 📫 Contact Ehsan Modiri - ehsan.modiri@ufz.de Pallav Kumar Shrestha - pallav-kumar.shrestha@ufz.de Institution Helmholtz Centre for Environmental Research - UFZ, Department of Computational Hydrosystems

Modiri, Ehsan · Shrestha, Pallav Kumar · Samaniego Eguiguren, Luis Eduardo

70 files · 34 GB · netcdfdeclared

Historical Hydrological Simulations over the South African Domain (1990-2024) The mHM's simulations of the Planet4Health project This dataset contains historical hydrological simulations for the South African domain (domain 1020011530) conducted with the Mesoscale Hydrological Model (mHM) at a spatial resolution of 0.015625°. The simulation period spans 1990-2024 and was part of the Planet4Health (P4H) project, utilising the ERA5 meteorological forcing. This archive is prepared for DOI assignment and ensures long-term reproducibility. It includes relevant clipped NetCDF components for soil moisture layers 2 and 3, consistent with the infrastructure provided within the Helmholtz Centre for Environmental Research (UFZ). The simulations were executed using a specific version of the mHM model with the SCC method for gauges, paired with the mRMv1.0 routing configuration. 🛰️ Simulation Details Model: Mesoscale Hydrological Model (mHM) Codebase: scc_for_gauges branch (https://git.ufz.de/shresthp/mhm/-/tree/scc_for_gauges?ref_type=heads) Spatial resolution: 0.015625° Temporal resolution: Daily Simulation period: 1990-2024 Simulation type: Historical simulation Spin-up: 30-year spin-up using 1990-2019 ERA5 climatology Model version: v1.0 Setup Scope: Model run for domain 1020011530, post-processed and clipped. Configuration & Modules The configuration utilises standard structural components with the SCC methodology. Modules included: Snow processes: Degree-day method Soil moisture: Feddes equation for evapotranspiration reduction Infiltration: Multi-layer Brooks-Corey-like approach Direct runoff: Linear reservoir exceedance method Potential evapotranspiration: Hargreaves-Samani method Interflow: Storage reservoir with nonlinear outflow Groundwater: Linear reservoir Routing: Adaptive time-step routing with mRMv1.0 mechanisms 📥 Input Datasets Meteorological Forcing: ERA5 (Hersbach et al., 2020) at a native input meteorological resolution of 0.25°, dynamically downscaled/mapped to model requirements. Processing Infrastructure: Tracked, processed, and validated under the Planet4Health deployment pipeline (https://git.ufz.de/planet4health/mhm_production/-/tree/main/postproc?ref_type=heads). Data Interfaces: Climate Data Interface version 2.2.4 (CDI) | Climate Data Operators version 2.2.2 (CDO) | NetCDF Operators version 5.1.7 (NCO). 📤 Output Variables sm_l02: Volumetric soil moisture layer 2 (50-150 mm depth) [mm mm-1, fraction between 0 and 1] sm_l03: Volumetric soil moisture layer 3 (150-300 mm depth) [mm mm-1, fraction between 0 and 1] 📫 Contact Ehsan Modiri - ehsan.modiri@ufz.de Pallav Kumar Shrestha - pallav-kumar.shrestha@ufz.de Institution Helmholtz Centre for Environmental Research - UFZ, Department of Computational Hydrosystems

Modiri, Ehsan · Shrestha, Pallav Kumar · Samaniego Eguiguren, Luis Eduardo

70 files · 33 GB · netcdfdeclared

Historical Hydrological Simulations over the South African Domain (1990-2024) The mHM's simulations of the Planet4Health project This dataset contains historical hydrological simulations for the South African domain (domain 1020011530) conducted with the Mesoscale Hydrological Model (mHM) at a spatial resolution of 0.015625°. The simulation period spans 1990-2024 and was part of the Planet4Health (P4H) project, utilising the ERA5 meteorological forcing. This archive is prepared for DOI assignment and ensures long-term reproducibility. It includes relevant clipped NetCDF components for soil water content layers 5 and 6, consistent with the infrastructure provided within the Helmholtz Centre for Environmental Research (UFZ). The simulations were executed using a specific version of the mHM model with the SCC method for gauges, paired with the mRMv1.0 routing configuration. 🛰️ Simulation Details Model: Mesoscale Hydrological Model (mHM) Codebase: scc_for_gauges branch (https://git.ufz.de/shresthp/mhm/-/tree/scc_for_gauges?ref_type=heads) Spatial resolution: 0.015625° Temporal resolution: Daily Simulation period: 1990-2024 Simulation type: Historical simulation Spin-up: 30-year spin-up using 1990-2019 ERA5 climatology Model version: v1.0 Setup Scope: Model run for domain 1020011530, post-processed and clipped. Configuration & Modules The configuration utilises standard structural components with the SCC methodology. Modules included: Snow processes: Degree-day method Soil moisture: Feddes equation for evapotranspiration reduction Infiltration: Multi-layer Brooks-Corey-like approach Direct runoff: Linear reservoir exceedance method Potential evapotranspiration: Hargreaves-Samani method Interflow: Storage reservoir with nonlinear outflow Groundwater: Linear reservoir Routing: Adaptive time-step routing with mRMv1.0 mechanisms 📥 Input Datasets Meteorological Forcing: ERA5 (Hersbach et al., 2020) at a native input meteorological resolution of 0.25°, dynamically downscaled/mapped to model requirements. Processing Infrastructure: Tracked, processed, and validated under the Planet4Health deployment pipeline (https://git.ufz.de/planet4health/mhm_production/-/tree/main/postproc?ref_type=heads). Data Interfaces: Climate Data Interface version 2.2.4 (CDI) | Climate Data Operators version 2.2.2 (CDO) | NetCDF Operators version 5.1.7 (NCO). 📤 Output Variables swc_l05: Soil water content layer 5 (500-1000 mm depth) [mm] swc_l06: Soil water content layer 6 (1000-2000 mm depth) [mm] 📫 Contact Ehsan Modiri - ehsan.modiri@ufz.de Pallav Kumar Shrestha - pallav-kumar.shrestha@ufz.de Institution Helmholtz Centre for Environmental Research - UFZ, Department of Computational Hydrosystems

Modiri, Ehsan · Shrestha, Pallav Kumar · Samaniego Eguiguren, Luis Eduardo

70 files · 34 GB · netcdfdeclared

Historical Hydrological Simulations over the South African Domain (1990-2024) The mHM's simulations of the Planet4Health project This dataset contains historical hydrological simulations for the South African domain (domain 1020011530) conducted with the Mesoscale Hydrological Model (mHM) at a spatial resolution of 0.015625°. The simulation period spans 1990-2024 and was part of the Planet4Health (P4H) project, utilising the ERA5 meteorological forcing. This archive is prepared for DOI assignment and ensures long-term reproducibility. It includes relevant clipped NetCDF components for soil water content layers 1 and 2, consistent with the infrastructure provided within the Helmholtz Centre for Environmental Research (UFZ). The simulations were executed using a specific version of the mHM model with the SCC method for gauges, paired with the mRMv1.0 routing configuration. 🛰️ Simulation Details Model: Mesoscale Hydrological Model (mHM) Codebase: scc_for_gauges branch (https://git.ufz.de/shresthp/mhm/-/tree/scc_for_gauges?ref_type=heads) Spatial resolution: 0.015625° Temporal resolution: Daily Simulation period: 1990-2024 Simulation type: Historical simulation Spin-up: 30-year spin-up using 1990-2019 ERA5 climatology Model version: v1.0 Setup Scope: Model run for domain 1020011530, post-processed and clipped. Configuration & Modules The configuration utilises standard structural components with the SCC methodology. Modules included: Snow processes: Degree-day method Soil moisture: Feddes equation for evapotranspiration reduction Infiltration: Multi-layer Brooks-Corey-like approach Direct runoff: Linear reservoir exceedance method Potential evapotranspiration: Hargreaves-Samani method Interflow: Storage reservoir with nonlinear outflow Groundwater: Linear reservoir Routing: Adaptive time-step routing with mRMv1.0 mechanisms 📥 Input Datasets Meteorological Forcing: ERA5 (Hersbach et al., 2020) at a native input meteorological resolution of 0.25°, dynamically downscaled/mapped to model requirements. Processing Infrastructure: Tracked, processed, and validated under the Planet4Health deployment pipeline (https://git.ufz.de/planet4health/mhm_production/-/tree/main/postproc?ref_type=heads). Data Interfaces: Climate Data Interface version 2.2.4 (CDI) | Climate Data Operators version 2.2.2 (CDO) | NetCDF Operators version 5.1.7 (NCO). 📤 Output Variables swc_l01: Soil water content layer 1 (0-50 mm depth) [mm] swc_l02: Soil water content layer 2 (50-150 mm depth) [mm] 📫 Contact Ehsan Modiri - ehsan.modiri@ufz.de Pallav Kumar Shrestha - pallav-kumar.shrestha@ufz.de Institution Helmholtz Centre for Environmental Research - UFZ, Department of Computational Hydrosystems

Modiri, Ehsan · Shrestha, Pallav Kumar · Samaniego Eguiguren, Luis Eduardo

72 files · 36 GB · netcdfdeclared

Historical Hydrological Simulations over the South African Domain (1990-2024) The mHM's simulations of the Planet4Health project This dataset contains historical hydrological simulations for the South African domain (domain 1020011530) conducted with the Mesoscale Hydrological Model (mHM) at a spatial resolution of 0.015625° . The simulation period spans 1990-2024 and was part of the Planet4Health (P4H) project, utilising the ERA5 meteorological forcing. This archive is prepared for DOI assignment and ensures long-term reproducibility. It includes relevant clipped NetCDF components (streamflow 'q', soil moisture 'sm_l01', domain mask, and uparea assets) , consistent with the infrastructure provided within the Helmholtz Centre for Environmental Research (UFZ) . The simulations were executed using a specific version of the mHM model with the SCC method for gauges, paired with the mRMv1.0 routing configuration. 🛰️ Simulation Details Model: Mesoscale Hydrological Model (mHM) Codebase: scc_for_gauges branch ( https://git.ufz.de/shresthp/mhm/-/tree/scc_for_gauges?ref_type=heads ) Spatial resolution: 0.015625° Temporal resolution: Daily Simulation period: 1990-2024 Simulation type: Historical simulation Model version: mHMv5.11.3 (Release mRMv1.0) Setup Scope: Model run for domain 1020011530, post-processed and clipped. Simulation Version: v1.0 Configuration & Modules The configuration utilises standard structural components with the SCC methodology. Modules included: Snow processes: Degree-day method Soil moisture: Feddes equation for evapotranspiration reduction Infiltration: Multi-layer Brooks-Corey-like approach Direct runoff: Linear reservoir exceedance method Potential evapotranspiration: Hargreaves-Samani method Interflow: Storage reservoir with nonlinear outflow Groundwater: Linear reservoir Routing: Adaptive time-step routing with mRMv1.0 mechanisms 📥 Input Datasets Meteorological Forcing: ERA5 (Hersbach et al., 2020) at a native input meteorological resolution of 0.25°, dynamically downscaled/mapped to model requirements. Processing Infrastructure: Tracked, processed, and validated under the Planet4Health deployment pipeline ( https://git.ufz.de/planet4health/mhm_production/-/tree/main/postproc?ref_type=heads ). Data Interfaces: Climate Data Interface version 2.2.4 (CDI) | Climate Data Operators version 2.2.2 (CDO) | NetCDF Operators version 5.1.7 (NCO). 📤 Output Variables q: Routed streamflow (discharge) [m3 s-1] sm_l01: Volumetric soil moisture of soil layer 1 (top 50 mm) [mm mm-1, fraction between 0 and 1] mask: Domain clipping structure [binary flag / dimensionless] uparea: Upstream catchment area matrix [m2] 📫 Contact For questions or collaboration inquiries, please contact: Ehsan Modiri - ehsan.modiri@ufz.de Pallav Kumar Shrestha - pallav-kumar.shrestha@ufz.de 📚 References Boeing, F. et al., 2022. Hydrol. Earth Syst. Sci. , 26, 5137-5161. Hargreaves, G.H. & Samani, Z.A., 1985. Applied Engineering in Agriculture , 1(2), pp.96-99. Hartmann, J. & Moosdorf, N., 2012. Geochem. Geophys. Geosyst. , 13(12). Hengl, T. et al., 2017. PLoS One , 12(2), e0169748. Hersbach, H. et al., 2020. QJRMS , 146(730), pp.1999-2049. Kumar, R. et al., 2013. Water Resources Research , 49(1), pp.360-379. Lehner, B. et al., 2011. Front. Ecol. Environ. , 9(9), pp.494-502. Rakovec, O. et al., 2016. J. Hydrometeorology , 17(1), pp.287-307. Rakovec, O. et al., 2022. Earth's Future , 10(3), e2021EF002394. Samaniego, L. et al., 2010. Water Resources Research , 46(5). Samaniego, L. et al., 2023. mhm-ufz/mHM: v5.13.1, Zenodo. DOI: 10.5281/zenodo.8279545 Thober, S. et al., 2019. Geosci. Model Dev. , 12(6), pp.2501-2521.

HUDA, SABIN

1 files · 729 MB · csvdeclared

AMLNet - Synthetic Anti-Money Laundering Benchmark Dataset, Version 2.0 Relation: Is new version of identifier: 10.5281/zenodo.16736515 AMLNet is a synthetic anti-money laundering benchmark dataset created for machine learning evaluation. This Version 2.0 release is associated with the paper: "AMLNet: A Knowledge-Guided Synthetic Benchmark for Machine Learning Evaluation in Anti-Money Laundering" The dataset contains a fixed synthetic benchmark instance generated using the AMLNet framework. It includes approximately 1.09 million transactions over a 195-day simulation period, from 13 October 2025 to 27 April 2026. The benchmark contains 1,411 suspicious transactions, corresponding to a suspicious rate of approximately 0.13%. The dataset is fully synthetic. The accounts, transactions, timestamps, locations, balances, metadata, labels, and customer activity patterns do not correspond to real customers, real institutions, or real banking activity. AMLNet was designed to support machine learning experiments under rare-event anti-money laundering conditions. The dataset includes ordinary transactions and suspicious transaction sequences representing structuring, layering, and integration patterns. Suspicious activity is embedded within ordinary account activity to make the detection task more realistic and non-trivial. CONTENTS This release includes: - the fixed AMLNet Version 2.0 synthetic transaction dataset; - transaction labels; - laundering typology labels; - transaction metadata; - dataset documentation and column descriptions. Evaluation scripts will be added to this Zenodo record after publication of the associated paper. The AMLNet generator source code is not included in this release due to security concerns. DATA FORMAT The main dataset is provided as a CSV file with the following columns: - step: Sequential simulation step or transaction index. - type: Transaction type, such as BPAY, CASH_OUT, DEBIT, EFTPOS, NPP, OSKO, PAYMENT, or TRANSFER. - amount: Transaction amount in Australian dollars. - category: Transaction category, such as housing, food, transport, recreation, healthcare, education, utilities, shell company, property investment, cryptocurrency, or other. - nameOrig: Originating account or customer identifier. - nameDest: Destination account, customer, or merchant identifier. - oldbalanceOrg: Originating account balance before the transaction. - newbalanceOrig: Originating account balance after the transaction. - isFraud: Binary label used for suspicious/fraudulent transaction detection. - isMoneyLaundering: Binary AML label, where 1 indicates suspicious money laundering activity and 0 indicates ordinary activity. - laundering_typology: Laundering typology label. Values include normal, structuring, layering, and integration. - metadata: JSON-style metadata containing timestamp, location, device information, payment method, risk indicators, and typology-specific details where applicable. - fraud_probability: Model-generated or risk-score field used in selected experiments. This field may be empty for some records. - hour: Hour of transaction. - day_of_week: Day of week. - day_of_month: Day of month. - month: Month number. LABELS The dataset includes two binary label fields: - isFraud: Binary suspicious/fraudulent transaction label. - isMoneyLaundering: Binary anti-money laundering label. The laundering_typology column provides the suspicious activity type for labeled suspicious transactions. Values include: - normal - structuring - layering - integration DATASET STATISTICS - Total transactions: approximately 1.09 million - Suspicious transactions: 1,411 - Suspicious transaction rate: approximately 0.13% - Simulation period: 195 days - Simulation dates: 13 October 2025 to 27 April 2026 - Generated customer accounts: 10,000 - Observed graph nodes: 11,000, including customer and merchant nodes - Transaction types: BPAY, CASH_OUT, DEBIT, EFTPOS, NPP, OSKO, PAYMENT, and TRANSFER - Payment identifiers: BSB_Account, CardNumber, and PayID - Laundering typologies: structuring, layering, and integration - Geographic setting: Australian synthetic banking context SPLIT AND EVALUATION PROTOCOL The associated manuscript describes the split protocol and evaluation protocol used in the reported experiments. For transaction-level experiments, transactions are ordered chronologically to reduce temporal leakage. For node-level graph experiments, the dataset is converted into an account/entity graph, and node features are computed from aggregated transaction statistics. The manuscript describes the chronological train, validation, and test protocol used for model evaluation. Evaluation scripts will be added to this Zenodo record after publication of the associated paper. SYNTHETIC DATA NOTICE This dataset is fully synthetic. It does not contain real customer records, real account information, real banking transactions, real IP addresses, or real financial institution data. All customer identifiers, merchant identifiers, balances, timestamps, locations, transaction patterns, labels, and metadata values were generated for research purposes. The dataset should not be interpreted as a sample of actual banking activity. GENERATOR SOURCE CODE The AMLNet generator source code is not included in this release due to security concerns. Requests for access to the generator source code may be considered for legitimate research purposes, subject to identity verification, institutional affiliation, and appropriate use conditions. The associated manuscript provides the generator pseudocode, main configuration details, demographic assumptions, regulatory constraints, laundering typologies, timing rules, routing rules, split protocol, and evaluation protocol. This public release provides the fixed generated dataset instance used in the associated paper. Evaluation scripts will be added to this Zenodo record after publication. USAGE This dataset can be used for: - anti-money laundering machine learning research; - rare-event classification experiments; - transaction-level suspicious activity detection; - account-level graph classification; - feature ablation studies; - explainability experiments; - synthetic-to-real transfer learning research; - educational and academic research on financial crime detection. LICENSE This dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International License. You may share and adapt the dataset for non-commercial purposes, provided that appropriate credit is given. Commercial use is not permitted without prior permission. For commercial licensing enquiries, please contact: s.huda@griffith.edu.au, hudasabin@gmail.com CITATION If you use this dataset, please cite the Zenodo dataset record and the associated paper: Huda, S., Foo, E., Newton, M. A. H., Jadidi, Z., Huda, S., Morgan, G., and Sattar, A. AMLNet: A Knowledge-Guided Synthetic Benchmark for Machine Learning Evaluation in Anti-Money Laundering. Under review. Dataset: Huda, S. et al. AMLNet Synthetic Anti-Money Laundering Benchmark Dataset, Version 2.0. Zenodo. 10.5281/zenodo.21237971 CONTACT For questions about the dataset, please contact: Sabin Huda School of Information and Communication Technology Faculty Member, Academy of Excellence in Financial Crime Investigation & Compliance Griffith University Email: s.huda@griffith.edu.au, hudasabin@gmail.com

Souza, Caio · Correia, João

54 files · 16 MB · csvdeclared

This repository contains the second version of the metamodel-based rescoring framework for protein-ligand binding affinity prediction. The first version introduced a linear metamodel combined with random train/test splits, but did not explicitly account for structural similarity or information leakage between training, validation, and test partitions. In this updated version, we included: Python scripts for data preprocessing, model training, and evaluation Pairwise ΔΔG evaluation code and associated data Visualization scripts for generating publication figures This dataset and codebase are intended to support reproducibility and further development of metamodel-based rescoring strategies in structural bioinformatics and computational drug design.

Costa, Carlos Fransley Scatambulo

3 files · 614 KB · csv, pdfdeclared

Dados anonimizados referentes ao estudo na tese: Formação Docente em Inteligência Artificial para o Ensino Superior: dos Fundamentos Computacionais ao Uso Crítico e Pedagógico da IA Generativa .