Rocco Palmitessa

Rocco Palmitessa

Auto-generated profile, based on publicly available information

Rocco Palmitessa

Technical University of Denmark, Department of Environmental and Resources Engineering, Section of Climate and Monitoring, Miljøvej B115, 2800 Kgs. Lyngby, Denmark

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2017 in Water Research
Verified
Journal Article
Open access
AMAnn-Kathrin McCall
Ann-Kathrin McCall
RPRocco Palmitessa
Rocco Palmitessa
FBFrank Blumensaat
Frank Blumensaat
EMEberhard Morgenroth
Eberhard Morgenroth
COChristoph Ort
Christoph Ort
To which extent illicit drugs are transformed during in-sewer transport, depends on a number of factors: i) substance-specific transformation rates, ii) environmental conditions, iii) point of discharge (location of drug user) and iv) sewer network properties, primarily hydraulic residence time (HRT) and the ratio of biofilm contact area to wastewater volume (A/Veq). Assessing associated uncertainties typically requires numerous simulations. Therefore, we propose a new two-step modeling framework: 1) Quantify hydrodynamic conditions. This computationally demanding step was performed once in SWMM to derive HRT and A/Veq for each potential point of discharge (node) in three catchments of different size. 2) Estimate biomarker loss. In this step, Monte Carlo simulations were performed for defined scenarios. Depending on assumptions about drug user distribution and prevalence, a number of nodes was sampled. For each node an empirical first-order transformation model was applied with flow-path-corresponding HRT and A/Veq from step 1. Biotic and abiotic transformation rates were sampled from distributions combining variability of different biofilms. In our modeling study, median losses were >30% for amphetamine, 6-monoacetylmorphine and 6-acetylcodeine in all three catchments with high uncertainty (5%-100% loss), which would imply a systematic underestimation of consumption when neglecting in-sewer processes. Median losses for 21 other investigated biomarkers were <10% with different uncertainty ranges - "no substantial transformation" was confirmed for nine substances in a real sewer segment with a 2-h residence time. Transferability of these results must be tested for other catchments. To further reduce uncertainty, mainly additional knowledge on transformation rates, particularly in biofilm, and their distribution across a sewer network is needed to update model input objectively. Our approach allows efficient testing and, furthermore, can be expanded for many other human biomarkers. Accounting for biomarker stability during in-sewer transport will avoid biased estimates and further improve wastewater-based epidemiology.

11 August 2022 in Water Research
Verified
Journal Article
Open access
RPRocco Palmitessa
Rocco Palmitessa
MGMorten Grum
Morten Grum
AEAllan Peter Engsig-Karup
Allan Peter Engsig-Karup
RLRoland Löwe
Roland Löwe
We propose and demonstrate a new approach for fast and accurate surrogate modelling of urban drainage system hydraulics based on physics-guided machine learning. The surrogates are trained against a limited set of simulation results from a hydrodynamic (HiFi) model. Our approach reduces simulation times by one to two orders of magnitude compared to a HiFi model. It is thus slower than e.g. conceptual hydrological models, but it enables simulations of water levels, flows and surcharges in all nodes and links of a drainage network and thus largely preserves the level of detail provided by HiFi models. Comparing time series simulated by the surrogate and the HiFi model, R2 values in the order of 0.9 are achieved. Surrogate training times are currently in the order of one hour. However, they can likely be reduced through the application of transfer learning and graph neural networks. Our surrogate approach will be useful for interactive workshops in initial design phases of urban drainage systems, as well as for real time applications. In addition, our model formulation is generic and future research should investigate its application for simulating other water systems.

1 September 2021 in Journal of Hydro-environment Research
Verified
Journal Article
Closed access
RPRocco Palmitessa
Rocco Palmitessa
PMPeter Steen Mikkelsen
Peter Steen Mikkelsen
MBMorten Borup
Morten Borup
Adrian Wing-Keung LawAdrian Wing-Keung Law
Adrian Wing-Keung Law

15 December 2020 in Journal of Hydroinformatics
Verified
Journal Article
Open access
PDF file
RPRocco Palmitessa
Rocco Palmitessa
PMPeter Steen Mikkelsen
Peter Steen Mikkelsen
ALAdrian W. K. Law
Adrian W. K. Law
MBMorten Borup
Morten Borup
Tunnels are increasingly used worldwide to expand the capacity of urban drainage systems, but they are difficult to monitor with sensors alone. This study enables soft sensing of urban drainage tunnels by assimilating water level observations into an ensemble of hydrodynamic models. Ensemble-based data assimilation is suitable for non-linear models and provides useful uncertainty estimates. To limit the computational cost, our proposed scheme restricts the assimilation and ensemble implementation to the tunnel and represents the surrounding drainage system deterministically. We applied the scheme to a combined sewer overflow tunnel in Copenhagen, Denmark, with two sensors 3.4 km apart. The downstream observations were assimilated, while those upstream were used for validation. The scheme was tuned using a high-intensity event and validated with a low-intensity one. In a third event, the scheme was able to provide soft sensing as well as identify errors in the upstream sensor with high confidence.

28 March 2022
Verified
Conference Paper
Open access
RPRocco Palmitessa
Rocco Palmitessa
OHOliver Gyldenberg Hjermitslev
Oliver Gyldenberg Hjermitslev
HJHeidi Egeberg Johansen
Heidi Egeberg Johansen
KAKarsten Arnbjerg-Nielsen
Karsten Arnbjerg-Nielsen
PBPeter Bauer-Gottwein
Peter Bauer-Gottwein
RLRoland Löwe
Roland Löwe
Flood warning systems are needed to plan mitigation measures and inform response strategies. The extent and dynamics of floods are typically predicted using physics-based hydrological models, which are computationally expensive and data assimilation is difficult. Deep-learning models can overcome these limitations, enabling fast predictions informed by multiple sources of data. Studies show this can be achieved while retaining or improving the level of detail and accuracy previously attainable. We, therefore, propose a deep-learning flood forecasting tool that combines multiple sources of readily available data to quickly generate flood extent maps, which can inform warnings.We train a neural network with U-NET architecture consisting of encoder and decoder convolutional modules. In the encoder module, features are extracted from the input and the data is downsampled to reduce complexity. Subsequently, the data is upsampled back to the original dimension in the decoder module and each 10 by 10 m pixel of the output image represents a flood prediction. The input to the neural network includes radar rainfall observations, LIDAR topographic scans, soil type and land use maps, groundwater depth simulations and previous inundation maps. All inputs are individually normalized and pre-processed. The rainfall observations are temporally aggregated to various intervals, hydrological features are highlighted in the topographic scans, and soil types and uses are grouped into categories.The model is trained and evaluated against a set of maps of surface water extent derived from Synthetic Aperture Radar (SAR) satellite observations. The predictions are scored against the target images by computing the critical success index (CSI), which measures the percentage of correct predictions among the total predicted of observed flooded areas. Permanent water bodies and areas where flooding is not captured by the satellite images (e.g. in forests) are masked out during both training and evaluation. The model is trained on a set of flooding events that occurred between 2018 and 2020 within the Jammerbugt Municipality in northern Denmark, which extends for about 850 km2. The model is validated on spatially independent data and tested on temporally independent events from the same study area.The proposed model yielded up to ~60% CSI with the test dataset, which is comparable to existing flood screening approaches. The test data included both fluvial and pluvial flooding as well as observed surface water in coastal areas. Large flooded areas were correctly predicted, while false negatives were frequently obtained for smaller areas. The overall performance of the proposed method is expected to improve by further tuning the model hyperparameters and by treating separately flood processes with different dynamics (e.g. pluvial vs. fluvial vs. coastal). These tradeoffs are compensated by the minimal computational time required to generate predictions once the model has been trained. Also, it is expected that the model can easily be transferred to other locations since it relies on local topographic information. The additional advantage of using a deep-learning approach is the ability to easily integrate alternative and additional data sources, which enables, for example, longer-term flood warnings driven by rainfall forecasts instead of observations.

27 March 2022
Verified
Conference Paper
Open access
RLRoland Löwe
Roland Löwe
RPRocco Palmitessa
Rocco Palmitessa
Alan Ensig-KarupAlan Ensig-Karup
Alan Ensig-Karup
MGMorten Grum
Morten Grum
Hydrodynamic models (numerical solutions of the Saint Venant equations) are at the core of simulating water movements in natural streams and drainage systems. They enable realistic simulations of water movement and are directly linked to physical system characteristics such as channel slope and diameter. This feature is important for man-made drainage structures as it enables straightforward testing of the effects of varying channel designs. In cities, models with hundreds up to tens of thousands of pipes are commonly used for drainage infrastructure. Their computational expense remains high and they are not suited for a systematic screening of design options, discussing water management options in workshops, as well as many real-time applications such as data assimilation.Hydrologists have developed many approaches to enable faster simulations. All of these do, however, compromise on the physical detail of the simulated processes (for example, by simulating only flows using linear reservoirs), and usually also on the spatial and temporal resolution of the models (for example, by simulating only flows between key points in the system). The link to physical system characteristics is thus lost. Therefore, it is challenging to incorporate such approaches into planning workflows where changing city plans require a constant revision of water management options.Recent advances in scientific machine learning enable the creation of fast machine learning surrogates for complex systems that preserve a high spatio-temporal detail and a physically accurate simulation. We present such an approach that employs generalized residue networks for the simulation of hydraulics in drainage systems. The key concept is to train neural networks that learn how hydraulic states (level, flow and surcharge volume) at all nodes and pipes in the drainage network evolve from one time step to another, given a set of boundary conditions (surface runoff). Training is performed against the output of a hydrodynamic model for a short time series.Once trained, the surrogates generate the same results as a hydrodynamic model in the same level of detail, and they can be used to quickly simulate the effect of many different rain events and climate scenarios. Considering pipe networks with 50 to 100 pipes, our approach achieves NSE values in the order of 0.95 for the testing dataset. Simulations are performed 10 to 50 times faster than the hydrodynamic model. Training times are in the order of 25 minutes on a single CPU. The surrogates are system specific and need to be retrained when the physical system changes. To minimize this overhead, we train surrogates for small subsystems which can subsequently be linked into a model for a large drainage network.Our approach is an initial application of scientific machine learning for the simulation of hydraulics that is readily combined with other recent developments. Future research should, in particular, explore the application of physics-informed loss functions for bypassing the generation of training data from hydrodynamic simulations, and of graph neural networks to exploit spatial correlation structures in the pipe network.