Minimum Input Data Research Articles

Predicting the Wear Amount of Tire Tread Using 1D−CNN

Since excessively worn tires pose a significant risk to vehicle safety, it is crucial to monitor tire wear regularly. This study aimed to verify the efficient tire wear prediction algorithm proposed in a previous modeling study, which minimizes the required input data, and use driving test data to validate the method. First, driving tests were conducted with tires at various wear levels to measure internal accelerations. The acceleration signals were then screened using empirical functions to exclude atypical data before proceeding with the machine learning process. Finally, a tire wear prediction algorithm based on a 1D−CNN with bottleneck features was developed and evaluated. The developed algorithm showed an RMSE of 5.2% (or 0.42 mm) using only the acceleration signals. When tire pressure and vertical load were included, the prediction error was reduced by 11.5%, resulting in an RMSE of 4.6%. These findings suggest that the 1D−CNN approach is an efficient method for predicting tire wear states, requiring minimal input data. Additionally, it supports the potential usefulness of the intelligent tire technology framework proposed in the modeling study.

Efficient Structural Damage Detection with Minimal Input Data: Leveraging Fewer Sensors and Addressing Model Uncertainties

In the field of structural damage detection through vibration measurements, most existing methods demand extensive data collection, including vibration readings at multiple levels, strain data, temperature measurements, and numerous vibration modes. These requirements result in high costs and complex instrumentation processes. Additionally, many approaches fail to account for model uncertainties, leading to significant discrepancies between the actual structure and its numerical reference model, thus compromising the accuracy of damage identification. This study introduces an innovative computational method aimed at minimizing data requirements, reducing instrumentation costs, and functioning with fewer vibration modes. By utilizing information from a single vibration sensor and at least three vibration modes, the method avoids the need for higher-mode excitation, which typically demands specialized equipment. The approach also incorporates model uncertainties related to geometry and mass distribution, improving the accuracy of damage detection. The computational method was validated on a steel frame structure under various damage conditions, categorized as single or multiple damage. The results indicate up to 100% accuracy in locating damage and up to 80% accuracy in estimating its severity. These findings demonstrate the method’s potential for detecting structural damage with limited data and at a significantly lower cost compared to conventional techniques.

Protein A-like Peptide Design Based on Diffusion and ESM2 Models

Proteins are the foundation of life, and designing functional proteins remains a key challenge in biotechnology. Before the development of AlphaFold2, the focus of design was primarily on structure-centric approaches such as using the well-known open-source software Rosetta3. Following the development of AlphaFold2, deep-learning techniques for protein design gained prominence. This study proposes a new method to generate functional proteins using the diffusion model and ESM2 protein language model. Diffusion models, which are widely used in image and natural language generation, are used here for protein design, facilitating the controlled generation of new sequences. The ESM2 model, trained on the basis of large-scale protein sequence data, provides a deep understanding of the context of the sequence, thus improving the model’s ability to generate biologically relevant proteins. In this study, we used the Protein A-like peptide as a model study object, combined the diffusion model and the ESM2 model to generate new peptide sequences from minimal input data, and verified their biological activities through experiments such as the BLI affinity test. In conclusion, we developed a new method for protein design that provides a novel strategy to meet the challenges of generic protein generation.

A Survey of Data-Driven Construction Materials Price Forecasting

The construction industry is heavily influenced by the volatility of material prices, which can significantly impact project costs and budgeting accuracy. Traditional econometric methods have been challenged by their inability to capture the frequent fluctuations in construction material prices. This paper reviews the application of data-driven techniques, particularly machine learning, in forecasting construction material prices. The models are categorized into causal modeling and time-series analysis, and characteristics, adaptability, and insights derived from large datasets are discussed. Causal models, such as multiple linear regression (MLR), artificial neural networks (ANN), and the least square support vector machine (LSSVM), generally utilize economic indicators to predict prices. The commonly used economic indicators include but are not limited to the consumer price index (CPI), producer price index (PPI), and gross domestic product (GDP). On the other hand, time-series models rely on historical price data to identify patterns for future forecasting, and their main advantage is demanding minimal data inputs for model calibration. Other techniques are also explored, such as Monte Carlo simulation, for both price forecasting and uncertainty quantification. The paper recommends hybrid models, which combine various forecasting techniques and deep learning-advanced time-series analysis and have the potential to offer more accurate and reliable price predictions with appropriate modeling processes, enabling better decision-making and cost management in construction projects.

Short communication: Dairy Victory™ Platform: A Novel Benchmarking Platform to Empower Economic Decisions on Dairy Farms.

In the face of diminishing economic margins, dairy farmers globally are compelled to maintain economic competitiveness. Benchmarking emerges as a strategic tool to establish new, achievable improvement objectives that balance ambition with practicality. This typically requires integrating diverse data sources such as feed, milk production, diet, and market prices. However, many farms lack essential, cow-level data like daily milk output and milk income over feed cost (IOFC), which hampers economic performance visibility and informed decision-making. To address this challenge, we introduce “Dairy Victory™ platform (DVP)” a novel cloud-based benchmarking platform designed to simplify complex analyses. The DVP uniquely calculates zootechnical and economic key performance indicators (KPIs) at the cow and herd levels and benchmarks these against a dynamically selected cohort of farms, facilitating comparisons across various farm sizes, and milk production levels. The primary objective of this paper is to demonstrate the utility of DVP as a decision-making tool in supporting farmers and consultants with both operational and strategic decisions. It emphasizes leveraging benchmarking information to enhance decision-making processes, thereby highlighting the significant value that DVP brings to farmers, consultants, and dairy farm stakeholders. Our study analyzed data from 712 farms from December 2023, focusing on several KPIs, such as milk production, milk quality, feed efficiency, and IOFC using Dairy Herd Improvement (DHI) records. This approach showcases DV's ability to utilize minimal data inputs for detailed analysis, leveraging peer performance to set desirable and/or achievable goals. We present a case study demonstrating how the DVP platform can guide dairy farms using anonymized peer data. This approach enables users to potentially improve their IOFC by up to 35%. Our findings highlight DVP's potential as a powerful tool for generating insightful analyses, simulations, and recommendations, primarily from test-day data, but also integrated with market and estimated data. This supports more strategic decision-making in dairy management, including automatic goal-setting based on peer performance.

Modelling and validating soil carbon dynamics at the long-term plot scale using the rCTOOL R package

We introduce rCTOOL, an open-source R package for carbon (C) turnover modelling, featuring comprehensive documentation and a user-friendly interface. As an enhanced version of the widely used Danish C-TOOL model, rCTOOL maintains minimal input data requirements and reliable performance, while addressing the original model's limitations in openness and documentation. To validate rCTOOL, we analysed topsoil Soil Organic Carbon (SOC) dynamics using data from the long-term Askov straw disposal experiment (1981–2019), which quantifies the impact of varying annual straw C inputs on SOC storage. Our validation shows an unbiased global prediction error of less than 10%, with a mean error of 1.1 Mg C/ha (CI -0.7–3.0 Mg C/ha). The discrepancies between observed and predicted values were primarily due to spatiotemporal variability represented by the block and year in the long-term field experiment. We demonstrate how rCTOOL is a reliable asset for diverse applications in SOC management and research.

Energy signature approach for retrofit prioritization: A proposal for building identification methodology

Amidst the urgent call for carbon reduction, retrofitting existing buildings for energy efficiency has become imperative. Nonetheless, the challenge of selecting suitable buildings for retrofitting persists. This paper proposes a method for identifying retrofit target buildings using the heating Energy Signature (ES) approach to achieve effective carbon reduction through retrofitting.The method involves comparing the actual ES, derived from monthly heating energy usage in existing buildings, with the optimal ES based on the building's physical performance to assess the need for retrofitting or behavioral improvements. It takes into account factors such as building physical characteristics, occupants’ heating behavior, and outdoor environment, integrating ES parameters like balance-point temperature (BPT) and heating sensitivity.In practical application, the proposed method involves four steps. Step 1 collects five essential building data inputs from the building user. Step 2 supplements this information using open-source platforms to calculate the optimal ES parameters. Step 3 computes both the actual and optimal ES, and Step 4 compares these to identify energy inefficiencies. The results are then presented in a user-friendly format for intuitive understanding.Offering novelty, this method accurately identifies the causes of building energy consumption, streamlines calculation processes, requires minimal input data, and yields intuitive results. It furnishes valuable insights for stakeholders engaged in retrofitting projects and holds potential for the effective implementation of building retrofit policies on a larger scale.

A new transferable deep learning approach for crop mapping

ABSTRACT Accurate crop mapping provides important information for government decision-making and agricultural management. Recent advancements in deep learning have significantly enhanced the capabilities of remote sensing-based crop mapping. In this study, we developed a new deep learning approach, DSH, which comprises three modules, DeepLabV3+ (D), channel self-attention (S), and histogram matching (H). The DeepLabV3+ module learns the spatial distribution of crops in the spatial and spectral dimensions. The channel self-attention module was used to enhance the weights of the important features. The histogram-matching module addresses the domain gap between the training and testing images and enhances the transferability of the DSH. In addition, the input data of the DSH are monthly synthesized Sentinel-2 data, thus relaxing the data collection requirements. The performance of the DSH was evaluated and benchmarked against HRNetV2, DeepLabV3+, and random forest (RF) at eight sites in the U.S. China, and France with different farming structures, climate conditions, and landscape complexities. Temporal transfer revealed that the classification performance of DSH improved as the growth season progressed, peaked in the peak growth season (August), and then declined at each study site. The DSH model trained during the peak growth season demonstrated superior temporal transferability. Spatial transfer experiments demonstrated that transferring DSH to sites with similar planting structures achieved higher precision than full spatial transfers. Spatiotemporal transfer experiments conducted at eight sites over three years (2020–2022) demonstrated an average overall accuracy (OA) of 88.1% for DSH, highlighting the importance of similar planting structures for effective spatiotemporal transfer. DSH outperformed HRNetV2, DeepLabV3+, and RF in OA, producer’s accuracy, and user’s accuracy at all eight study sites. Notably, DSH exhibited comparable performance during both the peak and full growth seasons, with an average OA of 93.9%. The classification accuracy of test images after histogram matching remained stable from 2020 to 2022, whereas the accuracy of raw test images fluctuated annually. This indicates that histogram matching is effective in improving the transferability of DSH. Embedding the channel self-attention module into the position of the high-level features had a more significant impact on improving DSH’s performance than other configurations. Visualizing features from the channel self-attention and high-level layers revealed that integrating the channel self-attention module with DeepLabV3+‘s high-level features significantly improved crop mapping by enhancing relevant semantic information. Overall, DSH exhibits robust spatiotemporal generalizability and requires minimal input data, making it suitable for large-scale crop mapping.

Machine learning models for outcome prediction in thrombectomy for large anterior vessel occlusion.

Predicting long-term functional outcomes shortly after a stroke is challenging, even for experienced neurologists. Therefore, we aimed to evaluate multiple machine learning models and the importance of clinical/radiological parameters to develop a model that balances minimal input data with reliable predictions of long-term functional independency. Our study utilized data from the German Stroke Registry on patients with large anterior vessel occlusion who underwent endovascular treatment. We trained seven machine learning models using 30 parameters from the first day postadmission to predict a modified Ranking Scale of 0-2 at 90 days poststroke. Model performance was assessed using a 20-fold cross-validation and one-sided Wilcoxon rank-sum tests. Key features were identified through backward feature selection. We included 7485 individuals with a median age of 75 years and a median NIHSS score at admission of 14 in our analysis. Our Deep Neural Network model demonstrated the best performance among all models including data from 24 h postadmission. Backward feature selection identified the seven most important features to be NIHSS after 24 h, age, modified Ranking Scale after 24 h, premorbid modified Ranking Scale, intracranial hemorrhage within 24 h, intravenous thrombolysis, and NIHSS at admission. Narrowing the Deep Neural Network model's input data to these features preserved the high performance with an AUC of 0.9 (CI: 0.89-0.91). Our Deep Neural Network model, trained on over 7000 patients, predicts 90-day functional independence using only seven clinical/radiological features from the first day postadmission, demonstrating both high accuracy and practicality for clinical implementation on stroke units.

Developing Water Quality Formulations for a Semi-Distributed Rainfall–Runoff Model

Hydrological modeling can be challenging due to significant data requirements and computational complexities. Hydrological models must be sufficiently complex to describe physical processes yet simple enough to use. This paper describes the development of a simplified watershed-scale input–output model to simulate runoff quantity and quality during a storm event. This work builds upon an existing semi-distributed rainfall–runoff model by adding calculations for pollutant concentrations based on simplified mass balance equations. The model was tested against various watershed examples of increasing complexity. The results show the change in peak flow and pollutant concentration in different areas of the watershed, demonstrating the model’s ability to account for the dynamics of runoff movement through the watershed. This paper advances watershed management by addressing data scarcity through the development of a simplified hydrological model that effectively incorporates spatial variability within a watershed while requiring minimal data input.

Meta-heuristic optimization algorithms based feature selection for joint moment prediction of sit-to-stand movement using machine learning algorithms

The sit-to-stand (STS) movement is fundamental in daily activities, involving coordinated motion of the lower extremities and trunk, which leads to the generation of joint moments based on joint angles and limb properties. Traditional methods for determining joint moments often involve sensors or complex mathematical approaches, posing limitations in terms of movement restrictions or expertise requirements. Machine learning (ML) algorithms have emerged as promising tools for joint moment estimation, but the challenge lies in efficiently selecting relevant features from diverse datasets, especially in clinical research settings. This study aims to address this challenge by leveraging metaheuristic optimization algorithms to predict joint moments during STS using minimal input data. Motion analysis data from 20 participants with varied mass and inertia properties are utilized, and joint angles are computed alongside simulations of joint moments. Feature selection is performed using the Manta Ray Foraging Optimization (MRFO), Marine Predators Algorithm (MPA), and Equilibrium Optimizer (EO) algorithms. Subsequently, Decision Tree Regression (DTR), Random Forest Regression (RFR), Extra Tree Regression (ETR), and eXtreme Gradient Boosting Regression (XGBoost Regression) ML algorithms are deployed for joint moment prediction. The results reveal EO-ETR as the most effective algorithm for ankle, knee, and neck joint moment prediction, while MPA-ETR exhibits superior performance for hip joint prediction. This approach demonstrates potential for enhancing accuracy in joint moment estimation with minimal feature input, offering implications for biomechanical research and clinical applications.

A data-driven bit projection system with motor yield prediction and advisory for directional drilling and well trajectory control

In the evolving of the oil and gas industry, where innovation and technological advancement are paramount, directional drilling stands as a pioneering technique that has revolutionized the extraction of hydrocarbon resources from beneath the Earth's surface. For drilling with mud motor, accurate projection of bit position from the latest survey and comprehensive evaluation of the current motor yield (MY) are essential to avoiding early well trajectory deviation and optimizing future directional plans. Currently, these responsibilities primarily rest on the shoulders of directional drillers (DDs), consuming valuable drilling operation time and being subject to biased human judgments. In this study, a data-driven bit projection system for directional drilling optimization and well trajectory control is developed. A kinematic model is first constructed for the projection of bit inclination (INC), azimuth (AZI), and north-east-vertical (NEV) in drilling with mud motors. Moreover, in scenarios involving curve section slide drilling, a machine learning model is developed to predict instant MYs observed between surveys, which is trained and tested on a dataset comprising drilling over 350 Delaware Basin curve section stands. Ultimately, a low MY reasoning algorithm is proposed to identify the dominant factor that causes the suboptimal MY output and provides recommendations for upcoming drilling plans. The proposed system is validated using 1189 vertical stands, 240 curve stands, and 1837 lateral stands from 17 different wells. The validation results illustrate that the bit NEV projection error averages below 0.82 ft for 90-foot surveys in vertical/lateral sections. In curve sections, the average MY prediction error is 0.96° one hundred feet or 7.6% in the relative sense and the average 30-foot bit NEV projection error is 0.228 ft, with the predicted MY as input. Compared with the physics-based bottomhole assembly (BHA) bending model and other data-driven approaches in the literature, the proposed system sees a large improvement in MY prediction and the bit NEV projection accuracies. With the minimal input data requirements, fast computation speed, and accurate projection/prediction results, the proposed bit projection system holds the opportunity of application in the autonomous directional drilling system, real-time drilling job evaluations, and well trajectory optimization.

Determination of parameters of radio emission sources

An important task requiring additional research is the analysis of algorithms for determining the carrier frequencies of broadband signals of various durations, allowing for a short pulse duration to reliably determine the parameters of the input signal with positive signal-to-noise ratios. The search for optimal ways to determine the parameters of radio emission sources with minimal input data under operating conditions as part of on-board radio monitoring systems. Methods for determining the frequency and phase characteristics of broadband and narrowband signals with a minimum signal duration (up to 1 microsecond) are presented. A modification of the guiding cosine algorithm has been developed to optimize the resources of the signal processing system. The proposed algorithms make it possible to reduce the amount of computing device resources used. The total computational complexity of the algorithms is relatively low, and the amount of memory used is acceptable for loading into computing nodes from on-board equipment. This work was supported by the Ministry of Science and Higher Education within the State assignment № 075-00701-24-07.

Optimizing MOF properties for seasonal heat storage: a machine learning approach

In the quest to enhance thermochemical energy storage using promising sorbents, this work presents a study on the optimization of Metal Organic Frameworks (MOFs) properties for gas sorption, with a focus on CO2 and H2O adsorption. Through the analysis of crystallographic descriptors, the study aims to streamline the selection of MOFs that could potentially exceed the performance of existing water sorbent pairs. A comprehensive comparison of sequential learning (SL) algorithms reveals a method for identifying the minimal set of descriptors that influence adsorption properties of MOFs. The protocol involves constructing and training machine learning (ML) models to determine the number of influential descriptors and utilizing SHAP analysis to evaluate their importance. Findings suggest that including only these critical descriptors in the exploration space reduces computational load. Notably, the COMBO and the FUELS algorithms consistently outshine random guessing, validating their efficacy in materials optimization. The challenge of accessing full adsorption properties across the entire coverage range is addressed by a computational screening procedure requiring minimal input data. This method suggests that some vanadium based MOFs, originally designed for different purposes, could surpass the current leading compounds for thermal energy storage, primarily due to their optimal Henry coefficient values for water adsorption.

A generic approach to estimate airborne concentrations of substances released by indoor spray processes using a deterministic 2-box model.

Sprays are used both in workplace and consumer settings. Although spraying has advantages, such as uniform distribution of substances on surfaces in a highly efficient manner, it is often associated with a high inhalation burden. For an adequate risk assessment, this exposure has to be reliably quantified. Exposure models of varying complexity are available, which are applicable to spray applications. However, a need for improvement has been identified. In this contribution, a simple 2-box approach is suggested for the assessment of the time-weighted averaged exposure concentration (TWA) using a minimum of input data. At the moment, the model is restricted to binary spray liquids composed of a non-volatile fraction and volatile solvents. The model output can be refined by introducing correction factors based on the classification and categorization of two key parameters, the droplet size class and the vapor pressure class of the solvent, or by using a data set of experimentally determined airborne release fractions related to the used spray equipment. A comparison of model results with measured data collected at real workplaces showed that this simple model based on readily available input parameters is very useful for screening purposes. The generic 2-box spray model without refinement overestimates the measurements of the considered scenarios in approximately 50% of the cases by more than a factor of 100. The generic 2-box model performs better for room spraying than for surface spraying, as the airborne fraction in the latter case is clearly overestimated. This conservatism of the prediction was significantly reduced when correction factors or experimentally determined airborne release fractions were used in addition to the generic input parameters. The resulting predictions still overestimate the exposure (ratio tool estimate to measured TWA > 10) or they are accurate (ratio 0.5-10). If the available information on boundary conditions (application type, equipment) does not justify the usage of airborne release fraction, room spraying should be used resulting in the highest exposure estimate. The model scope may be extended to (semi)volatile substances. However, acceptance may be compromised by the limited availability of measured data for this group of substances and thus may have limited potency to evaluate the model prediction.

Month-to-month all-cause mortality forecasting: a method allowing for changes in seasonal patterns.

Forecasting of seasonal mortality patterns can provide useful information for planning health-care demand and capacity. Timely mortality forecasts are needed during severe winter spikes and/or pandemic waves to guide policy-making and public health decisions. In this article, we propose a flexible method for forecasting all-cause mortality in real time considering short-term changes in seasonal patterns within an epidemiologic year. All-cause mortality data have the advantage of being available with less delay than cause-specific mortality data. In this study, we use all-cause monthly death counts obtained from the national statistical offices of Denmark, France, Spain, and Sweden from epidemic seasons 2012-2013 through 2021-2022 to demonstrate the performance of the proposed approach. The method forecasts deaths 1 month ahead, based on their expected ratio to the next month. Prediction intervals are obtained via bootstrapping. The forecasts accurately predict the winter mortality peaks before the COVID-19 pandemic. Although the method predicts mortality less accurately during the first wave of the COVID-19 pandemic, it captures the aspects of later waves better than other traditional methods. The method is attractive for health researchers and governmental offices for aiding public health responses because it uses minimal input data, makes simple and intuitive assumptions, and provides accurate forecasts both during seasonal influenza epidemics and during novel virus pandemics.

A computational method to study heat transfer in a helicopter turboshaft engine compartment for waste energy recovery purposes

It is important to take action to make aviation more energy-efficient and less pollutant. One of the approaches currently under development is waste energy recovery. This would be specially advantageous in turboshaft engines, which present an exhaust flow that is not being used for propulsive purposes and with high thermal residual energy that increases infrared signature of helicopters.To evaluate where to locate waste energy recovery devices such as thermoelectric generators or organic Rankine cycles the following is needed: temperatures of exhaust gas flow temperature and exhaust ducts wall temperature, i.e. hot source temperature, and engine compartment temperature, i.e. heat sink temperature. This variables are usually not known beforehand. The present paper develops a method that, with minimal data input, translates flight conditions and engine operation into conditions inside the engine compartment that are later applied to obtain heat transfer in the exhaust ducts, where the waste energy recovery should take place to minimize the influence on the engine. The procedure is based on an algorithm that uses Computational Fluid Dynamics (CFD) simulations validated with experiments.The main findings of this work are: (i) cruise flight velocity has minimal impact on engine compartment temperatures, but hover operation increases it by 5–16 K, (ii) cruise altitude significantly affects engine compartment temperature, with a 12 K difference between 2500 ft and 10000 ft, (iii) considering only the axial component of velocity in exhaust ducts may underestimate wall temperature, (iv) heat transfer in exhaust ducts can be estimated using empirical correlations for natural convection, multiplied by a specific factor, (v) non-invasive methods can recover 23.6 to 31.2 kW of heat from exhaust duct walls, potentially converting up to half of it into useful work.

The spatiotemporal distribution prediction method for distributed photovoltaic installed capacity based on power supply measurement data

Abstract With the anticipated expansion of distributed power grid integration in the foreseeable future, the consideration of distributed power’s impact on power balance becomes paramount in distribution network planning. In this research, we presented a novel approach for predicting the spatial and temporal distribution of distribution network planning areas, with a specific focus on estimating the installed capacity of distributed photovoltaic (PV) systems. Our method leveraged the saturated capacity of distributed PV, requiring minimal data inputs. By establishing a quantitative model that elucidated the relationship between installed distributed PV capacity and land area, we generated PV installed capacity evolution curves for various types of land. Subsequently, we derived the development coefficient of distributed PV installed capacity. By combining this coefficient with the current status of installed distributed PV capacity in the target area’s land parcels, we forecasted the spatial and temporal distribution of future distributed PV capacity within the region. The proposed prediction model held significant implications for the planning of new distribution networks. Additionally, this study predicted the installed distributed PV capacity for distinct land use types, including residential, commercial, and industrial land, using a regional power supply unit as a representative example. We employed the installed PV capacity unit to forecast the electricity loss rate and energy saving rate within the planning area. By validating the model and method through exemplary test results, we demonstrated the model’s feasibility and accuracy. Furthermore, our model effectively predicted the impact of distributed PV integration on overall load forecasting, thereby offering the power grid more precise load forecasting capabilities.

Operation of a solar power plant with dual-axis solar tracker

The paper evaluates the generation of electrical energy by a solar power plant equipped with a solar tracking system using the ASHRAE clear-sky method for calculating solar insolation. The mathematical algorithm uses the MathCad system with data export and analysis in Microsoft Excel. Collected over a month and the operation period in 2022–2023, data on electricity generation by solar stations characterised by an optimal constant angle of inclination of the solar panel and equipped with a solar tracking system were used. By taking into account the varying ambient temperature, dust content, and solar transmission by the solar panel coating, the given algorithm allowed electricity generation by a solar panel to be forecasted with an average absolute error ranging from 0.22 to 9.8. To determine solar insolation for a specific day and the geographical coordinates of the intended construction site of a solar power plant, a mathematical model was developed using MathCad software. The experimental and computational studies carried out on selected clear days, accounting for varying weather conditions, demonstrated the adequacy of this method and its applicability for forecasting electricity generation with different inclination angles of a solar panel. It was established that a solar power plant with a solar tracking system generated 37% more electricity per year than that with fixed solar panels. The ASHRAE Clear-Sky method for calculating solar insolation allows the amount of electricity generated for a specific region to be estimated with minimal input data. Further research will focus on defining and improving methods for forecasting electricity generation by a solar power plant on overcast days.

Exploring the Impact of Future Land Uses on Flood Risks and Ecosystem Services, With Limited Data: Coupling a Cellular Automata Markov (CAM) Model, With Hydraulic and Spatial Valuation Models

Land use changes can majorly affect many parameters that are directly or indirectly interlinked to various human-environmental systems, including hydrological processes and flood risks. The knowledge of future land cover changes is crucial for better managing human-environmental interactions and addressing potential environmental challenges, such as floods. In this work, the impact of future land cover changes in flood inundation is assessed, using a case study in northeast Indiana, US. A Cellular Automata Markov (CAM) model is applied, combining Geographic Information Systems (GIS) and Python, to predict land changes and provide future land cover maps, along with statistical validation measures. The land use map outputs are then used in a HEC-RAS hydraulic model, to test the different flooding impacts under a design storm, using the rain-on-grid routine. The results indicate that even slightly more urbanized and deforested areas can increase the potential flood extent. Furthermore, the impacts of these forecasted land cover changes are quantified in monetary terms, based on a spatial Ecosystem Services Valuation (ESV) model. The findings indicate that as certain land uses (mainly wetlands, followed by forests) give their place to build-up areas, barren land, or even agricultural lands, the ‘lost’ value due can reach 1.5 million USD in 2051. The novelty of this study lies in int integrated character, combining for the first time to our knowledge land cover forecast with hydrologic-hydraulic modelling and spatial ESV, showing thus the future changes, risks, and potential economic losses, respectively. This application uses the minimum necessary input data to perform the analyses, and all data and codes are publicly available, contributing thus to the transferability and reproducibility of the approach.