Region Models Research Articles

Optimising synthetic datasets for machine learning-based prediction of building damage due to tunnelling

Assessment of tunnelling-induced building damage is a complex Soil-Structure Interaction (SSI) probelm, influenced by numerous geometric and material parameters of both the soil and structures, and is characterised by strong non-linear behaviour. Currently, there is a trend towards developing data-driven models using Machine Learning (ML) to capture this complex behaviour. Given the scarcity of real data, which typically comes from specific case studies, many researchers have turned to creating extensive synthetic datasets via sophisticated and validated numerical models like Finite Element Method (FEM). However, the development of these datasets and the training of advanced ML algorithms present significant challenges. poses significant challenges. Reliance solely on parameter domains and ranges derived from case studies can lead to imbalanced data distributions and subsequently poor performance of models in less populated regions. In this paper, we introduce a strategy for designing optimal high-confidence datasets through an iterative procedure. This process begins with a systematic literature review to determine the importance of parameters, their ranges, and dependencies as they pertain to building damage induced by SSI. Starting with several hundred FEM simulations, we generate an initial dataset and assess its quality and impact through Sensitivity Analysis (SA) studies, statistical modelling, and re-sampling in statistically significant regions. This evaluation allows us to refine the model’s input space, seeking scenarios that mitigate output distribution imbalances. The procedure is repeated until the datasets achieve a satisfactory balance for training metamodels, minimising bias effectively. Our findings highlight the success of this approach in identifying an optimal and feasible input space that significantly reduces imbalanced distributions of output features. This approach not only proves effective in our study but also offers a versatile methodology that could be adapted to other disciplines aiming to generate high-quality synthetic datasets.

Estimating black carbon levels using machine learning models in high-concentration regions

Black carbon (BC) is emitted into the atmosphere during combustion processes, often in conjunction with emissions such as nitrogen oxides (NOx) and ozone (O3), which are also by-products of combustion. In highly polluted regions, combustion processes are one of the main sources of aerosols and particulate matter (PM) concentrations, which affect the radiative budget. Despite the high relevance of this air pollution metric, BC monitoring is quite expensive in terms of instrumentation and of maintenance and servicing. With the aim to provide tools to estimate BC while minimising instrumentation costs, we use machine learning approaches to estimate BC from air pollution and meteorological parameters (NOx, O3, PM2.5, relative humidity (RH), and solar radiation (SR)) from currently available networks. We assess the effectiveness of various machine learning models, such as random forest (RF), support vector regression (SVR), and multilayer perceptron (MLP) artificial neural network, for predicting black carbon (BC) mass concentrations in areas with high BC levels such as Northern Indian cities (Delhi and Agra), across different seasons. The results demonstrate comparable effectiveness among the models, with the multilayer perceptron (MLP) showing the most promising results. In addition, the comparability between estimated and monitored BC concentrations was high. In Delhi, the MLP shows high correlations between measured and modelled concentrations during winter (R2: 0.85) and post-monsoon (R2: 0.83) seasons, and notable metrics in the pre-monsoon (R2: 0.72). The results from Agra are consistent with those from Delhi, highlighting the consistency of the neural network's performance. These results highlight the usefulness of machine learning, particularly MLP, as a valuable tool for predicting BC concentrations. This approach provides critical new opportunities for urban air quality management and mitigation strategies and may be especially valuable for megacities in medium- and low-income regions.

Winter Wheat Mapping Method Based on Pseudo-Labels and U-Net Model for Training Sample Shortage

In recent years, the semantic segmentation model has been widely applied in fields such as the extraction of crops due to its advantages such as strong discrimination ability, high accuracy, etc. Currently, there is no standard set of ground true label data for major crops in China, and the visual interpretation process is usually time-consuming and laborious. The sample size also makes it difficult to support the model to learn enough ground features, resulting in poor generalisation ability of the model, which in turn makes the model difficult to apply in fine extraction tasks of large-area crops. In this study, a method to establish a pseudo-label sample set based on the random forest algorithm to train a semantic segmentation model (U-Net) was proposed to perform winter wheat extraction. With the help of the GEE platform, Winter Wheat Canopy Index (WCI) indicators were employed in this method to initially extract winter wheat, and training samples (i.e., pseudo labels) were built for the semantic segmentation model through the iterative process of “generating random sample points—random forest model training—winter wheat extraction”; on this basis, the U-net model was trained with multi-time series remote sensing images; finally, the U-Net model was employed to obtain the spatial distribution map of winter wheat in Henan Province in 2022. The results illustrated that: (1) Pseudo-label data were constructed using the random forest model in typical regions, achieving an overall accuracy of 97.53% under validation with manual samples, proving that its accuracy meets the requirements for U-Net model training. (2) Utilizing the U-Net model, U-Net++ model, and random forest model constructed based on pseudo-label data for 2022, winter wheat mapping was conducted in Henan Province. The extraction accuracy of the three models is in the order of U-Net model > U-Net++ model > random forest model. (3) Using the U-Net model to predict the winter wheat planting areas in Henan Province in 2019, although the extraction accuracy decreased compared to 2022, it still exceeded that of the random forest model. Additionally, the U-Net++ model did not achieve higher classification accuracy. (4) Experimental results demonstrate that deep learning models constructed based on pseudo-labels exhibit higher classification accuracy. Compared to traditional machine learning models like random forest, they have higher spatiotemporal adaptability and robustness, further validating the scientific and practical feasibility of pseudo-labels and their generation strategies, which are expected to provide a feasible technical pathway for intelligent extraction of winter wheat spatial distribution information in the future.

Comparing the hybrid-lumped-LSTM model with a semi-distributed model for improved hydrological modeling

ABSTRACT Accurate hydrological modeling is essential for understanding and managing water resources. This study conducts a comparative analysis of hydrological modeling strategies in a date-scarce region. This study examines lumped (IHACRES), semi-distributed (HEC-HMS), and hybrid-lumped/long short-term memory (LSTM) models, aiming to assess their performance and accuracy in a data-scarce region. It investigates whether lump models can accurately simulate flow and evaluates the impact of combining lump models with machine learning to enhance accuracy, compared to semi-distributed models. The IHACRES model underestimates discharge, but its commendable NSE during calibration (0.628) and validation (0.681) signifies reliable simulation. The HEC-HMS model accurately depicts daily streamflow but struggles with extreme events, showcasing limitations in predicting maximum flows. The hybrid-lumped/LSTM model exhibits improved accuracy over IHACRES. Despite some underestimation, it mitigates IHACRES limitations during extreme events. However, challenges persist in simulating high flows, emphasizing the necessity for further refinement. The findings contribute to the discourse on merging machine learning with traditional hydrological models in data-scarce regions. The hybrid model offers promise but underscores the need for ongoing research to optimize performance, especially during extreme events. This study provides valuable insights for advancing hydrological modeling capabilities in complex watersheds.

An Earthquake Ground-Motion Model for Southwest Iberia

ABSTRACT Ground-motion models (GMMs) are fundamental for the estimation of ground shaking for probabilistic seismic hazard assessment. Because of the paucity of ground motion recordings in regions of low seismicity, stochastic approaches are often employed to generate synthetic data. In this study, we developed a GMM using a stochastic simulation approach for southwest Iberia—a zone for which seismic hazard is usually assessed using models developed for other regions. We collected geological, tectonic, and ground-motion data for offshore and inland Iberia, and calibrated several parameters for a stochastic simulation. The resulting synthetic response spectra were used to train a machine learning algorithm (artificial neural network) capable of predicting peak ground acceleration, peak ground velocity, and spectral acceleration on rock (VS30=760 m/s), along with the associated between-event and within-event terms. The resulting model was compared against other existing models for stable continental regions and ground-motion recordings for Portugal and Spain. The results indicate a good agreement with observations and the model can be used directly in probabilistic seismic hazard analysis for southwest Iberia.

Current genomic deep learning models display decreased performance in cell type specific accessible regions.

A number of deep learning models have been developed to predict epigenetic features such as chromatin accessibility from DNA sequence. Model evaluations commonly report performance genome-wide; however, cis regulatory elements (CREs), which play critical roles in gene regulation, make up only a small fraction of the genome. Furthermore, cell type specific CREs contain a large proportion of complex disease heritability. We evaluate genomic deep learning models in chromatin accessibility regions with varying degrees of cell type specificity. We assess two modeling directions in the field: general purpose models trained across thousands of outputs (cell types and epigenetic marks), and models tailored to specific tissues and tasks. We find that the accuracy of genomic deep learning models, including two state-of-the-art general purpose models - Enformer and Sei - varies across the genome and is reduced in cell type specific accessible regions. Using accessibility models trained on cell types from specific tissues, we find that increasing model capacity to learn cell type specific regulatory syntax - through single-task learning or high capacity multi-task models - can improve performance in cell type specific accessible regions. We also observe that improving reference sequence predictions does not consistently improve variant effect predictions, indicating that novel strategies are needed to improve performance on variants. Our results provide a new perspective on the performance of genomic deep learning models, showing that performance varies across the genome and is particularly reduced in cell type specific accessible regions. We also identify strategies to maximize performance in cell type specific accessible regions.

Assessment of Soil Temperature and Its Change Trends in the Permafrost Regions of the Northern Hemisphere

In this paper, we used data from 42 soil temperature observation sites in permafrost regions throughout the Northern Hemisphere to analyze the characteristics and variability in soil temperature. The observation data were used to evaluate soil temperature simulations at different depths from 10 CMIP6 models in the permafrost region of the Northern Hemisphere. The results showed that the annual average soil temperature in the permafrost regions in the Northern Hemisphere gradually decreased with increasing latitude, and the soil temperature gradually decreased with depth. The average soil temperatures at different depths were mainly concentrated around 0 °C. The 10 CMIP6 models performed well in simulating soil temperature, but most models tended to underestimate temperatures compared to the measured values. Overall, the CESM2 model yielded the best simulation results, whereas the CNRM-CM6-1 model performed the worst. The change trends in annual average soil temperature across the 42 sites ranged from −0.17 °C/10a to 0.41 °C/10a from 1900 to 2014, the closer to the Arctic, the faster the soil warming rate. The rate of soil temperature change also varied at different depths between 1900–2014 and 1980–2014. The rate of soil temperature change from 1980 to 2014 was approximately three times greater than that from 1900 to 2014.

Added value of EURO-CORDEX downscaling over the complex orography region of the Pyrenees

This study presents an assessment of the added value of downscaling utilizing Regional Climate Models (RCMs) compared to Global Climate Models (GCMs) in the high mountain region of the Pyrenees, characterized by complex topography. The EURO-CORDEX ensemble was investigated, employing a gridded high-resolution observational database as a reference. A recently proposed method is applied to quantify the performance gains or losses associated with dynamic downscaling. Our analysis focuses on calculating the added value by exploring the extremes of the Probability Density Function (PDF), spatial distribution patterns, and its relationship with elevation. Overall, our findings reveal significant improvements in the representation and general characterization of precipitation, minimum temperature, and maximum temperature in the Pyrenean region. Furthermore, RCMs demonstrate enhanced performance in capturing maximum precipitation events; however, they struggle to represent low precipitation rates, particularly in the Mediterranean area of the mountain range. Regarding temperature extremes, dynamical downscaling exhibits improvements in capturing maximum events. Nevertheless, deficiencies are observed in the RCMs’ representation of minimum temperature events for both minimum and maximum temperature variables, as well as in representing near-freezing temperatures.

Electromagnetic informed data model considerations for near-field DOA and range estimates

Localizing sources in the near-field is one of the emerging challenges for array signal processing, which has received a great deal of attention in recent years. The development of accurate localization algorithms requires the definition of a reliable model of the received signal that takes into account all wavefront characteristics, such as angle, range, and polarization, as well as electromagnetic effects, such as mutual coupling between antennas and the amplitude and phase behaviour of electromagnetic wavefronts. A system model that considers the electromagnetic-informed wave behaviour effects, independent of the type of receiver antennas, array structure, degree of correlation of sources signals and other electromagnetic effects, is considered an “ exact model ” in the literature. However, due to the mathematical complexity of this modeling approach, simplifications using several approximations are conventionally used. For instance, the phase of the exact model is approximated using the Fresnel approximation, while the magnitude of the exact model is simplified by assuming equal distances between the source and all elements in the array. In this work, we evaluate the accuracy of a localization algorithm, the multiple signal classification (MUSIC), using the exact and approximated models in the near-field region. Through a series of simulations, we demonstrate that the localization algorithm designed based on the electromagnetic-informed exact model outperforms the one designed using the approximated model. We also show that considering electromagnetic factors in the system model through the exact model results in a 13% improvement in the direction of arrival (DOA) root mean square error (RMSE) and a 57.7% improvement in range RMSE at signal-to-noise ratio (SNR) of 15 dB.

Performance Analysis of Random Forest Algorithm in Automatic Building Segmentation with Limited Data

Airborne laser technology produces point clouds that can be used to build 3D models of buildings. However, the work is a laborious process that could benefit from automation. Artificial intelligence (AI) has been widely used in automating building segmentation as one of the initial stages in the 3D modeling process. The algorithms with a high success rate using point clouds for automatic semantic segmentation are random forest (RF) and PointNet++, with each algorithm having its own advantages and disadvantages. However, the training and testing data to develop and test the model usually share similar characteristics. Moreover, producing a good automation model requires a lot of training data, which may become an issue for users with a small amount of training data (limited data). The aim of this research is to test the performance of the RF and PointNet++ models in different regions with limited training and testing data. We found that the RF model developed from a small amount data, in different regions between the training and testing data, performs well compared to PointNet++, yielding an OA score of 73.01% for the RF model. Furthermore, several scenarios have been used in this research to explore the capabilities of RF in several cases.

Using eddy-covariance to measure the effects of COVID-19 restrictions on CO2 emissions in a neighborhood of Indianapolis, IN

Eddy-covariance (EC) flux measurements in Indianapolis were used to quantify the impact of the COVID-19 lockdown on CO and CO2 emissions from a highway and a suburban neighborhood. CO2 fluxes were measured for 6 weeks pre-lockdown (January 22, 2020–March 3, 2020) and during lockdown (March 25, 2020– May 5, 2020) using EC instrumentation at 41 m AGL. Fossil fuel CO2 emissions (CO2ff) were estimated by calculating eddy diffusivity to obtain CO flux and then scaling by the CO:CO2ff emissions ratio (RCO). Flux measurements segregated by wind direction were compared to hourly emissions from the 2020 Hestia inventory model. The lockdown CO2ff average weekday emissions from the highway estimated by EC decreased by 51.5 ± 10.9% (11.2 ± 2.2 µmol m−2 s−1) compared to pre-lockdown, similar to Hestia’s estimate 56 ± 7% (12 ± 1 µmol m−2 s−1). The EC measurements detected a significant (2.2 ± 0.7 µmol m−2 s−1) but smaller magnitude decrease in CO2ff emissions from the suburban neighborhood. The daily cycles of CO2ff emissions were significantly correlated with Hestia estimates from the highway but not from the suburbs. This study demonstrates that EC flux towers and high-resolution inventory models in regions with mixed and spatially heterogeneous sources can quantify abrupt changes in sector- and source-specific CO2 fluxes.

The Green Bank 820 MHz Pulsar Survey. I. Survey Overview and Initial Results

The Green Bank 820 MHz pulsar survey covers ≃173 deg2 in the Cygnus X region of the Galaxy, centered on l = 84.°5 and b = 1.°5. Significant star formation is present in this region, and lines of sight pass through three arms of the Galaxy (Orion–Cygnus, Perseus, and an outer arm). Using the Green Bank Telescope, we recorded 200 MHz of bandwidth for 4.5 minutes at 81.92 μs resolution for each of 3457 observed survey pointings during 2016 and 2017, covering about two-thirds of the total area. We searched these data for pulsars and report the discovery of six new pulsars—PSRs J2016+3820, J2016+4231, J2019+3810, J2035+3538, J2035+3655, and J2041+4551—and the codiscovery of PSR J2057+4701. PSR J2035+3655 is in a short (4.5 hr) binary orbit; we report the full binary solution and weakly constrain the mass of the pulsar via a marginal (2σ) detection of the Shapiro delay. We also searched the survey data for known pulsars to estimate the survey’s sensitivity and measured 820 MHz pulse widths and flux density for 20 detected sources. For sources that were also detected in the Green Bank North Celestial Cap survey at 350 MHz, we measure scattering parameters and compare to expectations for the region. With these results, we revisit the population estimates that motivated this survey and consider the impact of the survey’s yield on their underlying models. We note an apparent underestimate in dispersion measure predictions from typical Galactic electron density models in the survey region, and discuss future observation strategies.

Implementation and validation of a generalized wall stress function

The generalized wall function by Shih et al. [Report No. M-1999-209398 (1999)], which accounts for non-equilibrium effects by the presence of favorable and adverse pressure gradients in turbulent flows, is addressed with the aim of performing high Reynolds number large-eddy simulations of the wall-bounded flow. The model uses a corrected law of the wall with a pressure gradient contribution to approximate the wall stress and applies to the entire viscous layer, buffer layer, and inertial region. A fully developed channel flow is first tested to validate the solver and model implementation, and then the wall function is assessed for the flow over a periodic hill. Wall-resolved simulations are in good agreement with reference results. A priori investigation with own experimental results corroborates the mathematical form of the model and suggests using different coefficients. The wall-modeled simulations show that the implemented wall model is able to improve the wall shear stress predictions compared to a standard equilibrium wall model. It corrects the underestimation of wall shear stresses by equilibrium models in the favorable pressure gradient region and the overestimation of wall shear stresses in the adverse pressure gradient region. The positions of the separation and reattachment points are also in good agreement with reference results. Furthermore, the prediction of the wall shear stress maximum in the favorable pressure gradient zone at the windward side of the hill is quite robust against coarsening the wall-normal grid spacing.

First Constraints on the Interstellar Medium Conditions of a Low-mass, Highly Obscured z = 4.27 Main-sequence Galaxy

We present the molecular gas content and interstellar medium conditions of MACS J0717_Az9, a strong gravitationally lensed z = 4.273, M * ≃ 2 × 109 M ⊙ star-forming galaxy with an unusually high (∼80%) obscured star formation fraction. We detect CO (4–3) in two independent lensed images, as well as [N ii] 205 μm, with the Atacama Large Millimeter Array. We derive a molecular gas mass of log 10[MH2(M⊙)]=9.77 , making it moderately deficient in molecular gas compared to the lower-redshift gas fraction scaling relation. Leveraging photodissociation region (PDR) models, we combine our CO (4–3) measurements with existing measurements of the [C ii] 158 μm line and total infrared luminosity to model the PDR conditions. We find PDR conditions similar to those in local star-forming galaxies, with a mean hydrogen density log10[n H cm−3] = 4.80 ± 0.39 and a mean radiation field strength log10[G 0 Habing] = 2.83 ± 0.26. Based on Band 3 continuum data, we derive an upper limit on the intrinsic dust mass of log10[M dust(M ⊙)] < 7.73, consistent with existing estimates. We use the 3D tilted-ring model fitting code 3D-Barolo to determine the kinematic properties of the CO (4–3) emitting gas. We find that it is rotationally dominated, with a V/σ = 4.6 ± 1.7, consistent with the kinematics of the [C ii]. With PDR conditions remarkably similar to those in normal dusty star-forming galaxies at z < 0.2 and a stable molecular disk, our observations of Az9 suggest that the dust-obscured phase for a low-mass galaxy at z ∼ 4 is relatively long. Thus, Az9 may be representative of a more widespread population that has been missed owing to insufficiently deep existing millimeter surveys.

Кластерный анализ геофизических полей при тектоническом районировании Африкано-Антарктического сектора Южного океана

The tectonic zoning of the African-Antarctic sector of the Southern Ocean was carried out on the basis of cluster analysis of a large volume of heterogeneous geophysical and geological data. It is known that the degree of geological and geophysical exploration of this part of the ocean by marine surveys and drilling remains extremely low. The results of such an analysis make it possible in areas with weak geophysical knowledge to quickly draw up tectonic zoning schemes based on regional geophysical data that are freely available throughout the entire territory of the world ocean and use them as a basis for further interpretation. The following materials were used as input data or classification features: ocean floor topography, gravity anomalies in free air and in the Bouger reduction, ∆Ta anomalous magnetic field model, ocean floor age, geoid height data, and the SL2013sv seismotomography model. «K-means» algorithms and the «Gaussian mixtures» method used for clustering. Based on the results of the application of these algorithms, cluster models of the study region were obtained, in which the selected classes fully reflect the main tectonic elements.

Heavy photophobic ALP at the LHC

We study the photophobic ALP model in high-mass regions under LHC Run-II. Since the ALP is predominantly coupled with electroweak gauge bosons such as ZZ, WW, and Zγ, and less with di-photon, the model may be probed via multi-boson final-state processes. We find that on-shell ALP productions with Zγ final states currently provide the best sensitivities for ma > 40 GeV.

Non-invasive biomonitoring of polar bear feces can be used to estimate concentrations of metals of concern in traditional food.

The Arctic faces increasing exposure to environmental chemicals such as metals, posing health risks to humans and wildlife. Biomonitoring of polar bears (Ursus maritimus) can be used to quantify chemicals in the environment and in traditional foods consumed by the Inuit. However, typically, these samples are collected through invasive or terminal methods. The biomonitoring of feces could be a useful alternative to the current metal monitoring method within the Arctic. Here, we aim to 1) quantify the relationship between concentrations of metals in the feces and tissues (muscle, liver, and fat) of polar bears using predictive modeling, 2) develop an easy-to-use conversion tool for use in community-based monitoring programs to non-invasively estimate contaminant concentrations in polar bears tissues and 3) demonstrate the application of these models by examining potential exposure risk for humans from consumption of polar bear muscle. Fecal, muscle, liver, and fat samples were harvested from 49 polar bears through a community-based monitoring program. The samples were analyzed for 32 metals. Exploratory analysis indicated that mean metal concentrations generally did not vary by age or sex, and many of the metals measured in feces were positively correlated with the internal tissue concentration. We developed predictive linear regression models between internal (muscle, liver, fat) and external (feces) metal concentrations and further explored the mercury and methylmercury relationships for utility risk screening. Using the cross-validated regression coefficients, we developed a conversion tool that contributes to the One Health approach by understanding the interrelated health of humans, wildlife, and the environment in the Arctic. The findings support using feces as a biomonitoring tool for assessing contaminants in polar bears. Further research is needed to validate the developed models for other regions in the Arctic and assess the impact of environmental weathering on fecal metal concentrations.

Principais fatores da avaliação da qualidade acadêmica para programas de pós-graduação: uma análise comparativa

Objective. This article derives from a research study that aims to identify the primary factors in assessing the academic quality of postgraduate programs, as applied by various self-assessment models in the Ibero-American region. Methodology. A qualitative investigation was conducted using comparative education methods to analyze seven existing self-assessment models in Chile, Ecuador, Central America, Colombia, and Spain. Units of analysis were established to compare the criteria and evidence of each model, utilizing individual and unified matrices to systematize all studied elements. Results. The findings identified levels of relevance between the factors and their corresponding evidence in determining the quality of a graduate program. Conclusion. Among all the proposed categories for analysis, the three most important are pedagogical factors, administrative factors, and impact assessment.

Performance Characteristics of an Infrared Photodetector Using Intersuband Junctions in Quantum Wells Based on Gallium Nitride

A simulation procedure for analyzing the electrical and optical characteristics of an AlGaN/GaN intersubbandquantum well middle-wavelength infrared photodetector is presented. The photoconductive gain spectrumwas simulated by coupling the drift-diffusion and capture-escape models in the active region of the devicestructure and by ignoring the contribution of radiative emission. It was shown that the photodetector at zero biasis sensitive over a spectral range from 4 to 6 μm, with the peak absorption occurring at 4.64 μm. The dependenceof the available photocurrent on both the wavelength and the angle of incidence of an unpolarized monochromaticbeam of light was also evaluated. An assessment of the dark current characteristics was estimated at varioustemperatures.

Divertor-safe nonlinear burn control based on a SOLPS parameterized core-edge model for ITER

For ITER operations, the range of desirable burning-plasma regimes with high fusion power output will be restricted by various operational constraints. These constraints include the saturation of ITER’s various heating and fueling actuators such as the neutral beam injectors, the ion and electron cyclotron heating systems, the gas puffing system, and the deuterium–tritium pellet injectors. In addition to these actuator constraints, the H-mode power threshold, divertor detachment, and the heat load on the divertor targets may apply limitations to ITER’s operational space. In this work, Plasma Operation Contour (POPCON) plots that map the aforementioned constraints to the temperature-density space are used to investigate which constraints are most limiting towards accessing regimes with high fusion power output. The presented POPCON plots are based on a control-oriented core-edge model that couples the nonlinear density and energy response models for the core-plasma region with SOLPS4.3 parameterizations for conditions in the edge-plasma regions (scrape-off-layer and divertor). Using this control-oriented core-edge model, a nonlinear burn controller, which aims to regulate the plasma temperature and density in the core-plasma region, is constructed in this work. This controller is augmented with an online optimization scheme that governs the control references such that the plasma can be guided towards regimes with high fusion powers while protecting the divertor targets from dangerously high heat loads. A closed-loop simulation study illustrates the capability of this burn control scheme.