In-field Conditions Research Articles

Direct Current to Digital Converter (DIDC): A Current Sensor.

This paper introduces a systematic approach to the design of Direct Current-to-Digital Converter (DIDC) specifically engineered to overcome the limitations of traditional current measurement methodologies in System-on-Chip (SoC) designs. The proposed DIDC addresses critical challenges such as high power consumption, large area requirements, and the need for intermediate analog signals. By incorporating a current mirror in a cascode topology and managing the current across multiple binary-sized branches with the Successive Approximation Register (SAR) logic, the design achieves precise current measurement. A simple comparator, coupled with an isolation circuit, ensures accurate and reliable sensing. Fabricated using the TSMC 180 nm process, the DIDC achieves 8-bit precision without the need for nonlinearity calibration, showcasing remarkable energy efficiency with an energy per conversion of 1.52 pJ, power consumption of 117 µW, and a compact area of 0.016 mm². This innovative approach not only reduces power consumption and area, but also provides a scalable and efficient solution for next-generation semiconductor technologies. The ability to conduct online measurements during both standard operations and in-field conditions significantly enhances the performance and reliability of SoCs, making this DIDC a promising advancement in the field.

Sound insulation characterisation of innovative natural ventilated façade in the context of living lab installations

Building acoustic standards like EN 14351 and ISO 10140 regulate the measurement of sound insulation of transparent elements, with indications of the test sample dimensions, test conditions, and criterions of adaptations of the results to different on-site conditions. However, given the research on innovative transparent building envelope including internal ventilation as double skin facades, these methodologies present limitations related to the characterization of the high variability of operating conditions in real in-field conditions. To this aim the acoustic performance could be explored with more flexible methods inside the multi-domain context of Living Labs, which present an opportunity for multiple characterizations and testing costs reduction. This work investigates the possibility of using the sound-intensity probe method to evaluate the airborne sound insulation of a transparent building element with internal ventilation. For this purpose, a comparative measurement campaign has been performed on the same building element installed in two Living Labs. The results show good compatibility between the different measurements and scales supporting the application of this methodology for comparative studies in the perspective of innovative building components measurements, and the application in Living Labs.

Environmentally Sustainable Detection of Arsenic using Convolutional Neural Networks and Imidazole-Based Organic Probes: Application in Food Samples and Arsenic Album.

Arsenic contamination poses a significant health risk, particularly when it infiltrates water supplies. While current detection methods offer precise analysis, they often involve complex instrumentation not suitable for field use. This study presents a novel approach by developing two probes, A1 and A2, based on 4-diethylaminosalicyladehyde, 2-hydroxy-1-naphthaldehyde, and 1,2-diaminoanthraquinone. These probes are highly sensitive and selective for detecting arsenite (As(III)) and arsenate (As(V)) in water, food samples, and homeopathic medicine with limits of detection in the nanomolar range. To elaborate our contribution to on-site arsenic detection, we introduce a convolutional neural network-based image recognition system. This system interprets images of the probes' colorimetric response, effectively categorizing different ranges of arsenic concentrations in parts per million (ppm). Our approach offers a real-time, cost-effective, and user-friendly solution for arsenic detection, extending its applicability from scientific laboratories to in-field conditions and even household monitoring. The findings fill critical research gaps in real-time detection methods, potentially revolutionizing the way we monitor environmental contaminants like arsenic.

Leveraging SUMO for Real-World Traffic Optimization: A Comprehensive Approach

This paper illuminates the utilization of SUMO as a powerful tool for addressing real-world traffic management issues. There is a gap in testing and validating solutions to in-field conditions due to the high cost and complexity of urban and suburban road networks. The validation step is often skipped, which can lead to a higher risk in implementing sophisticated solutions that exist in our multimodal transportation environment. This challenge is addressed by introducing simulations as a crucial preliminary step before real-world application. Accurate simulations require detailed data on intersection geometries, vehicle distribution, and driver behavior to accurately mirror real-world conditions. To meet these criteria, detailed sensor data on trajectories, types of road users, and their locations are extensively employed. This data forms the foundation for calibrated traffic simulations by NoTraffic™ . In conclusion, an in-depth demonstration of the method used to address a real-world traffic problem with SUMO is provided, emphasizing SUMO’s effectiveness in building confidence for deploying solutions in the field.

New productive pear variety Favoritka

The results of the selection and variety study of pears in the conditions of the Southern Urals are considered. At the South Ural Research Institute of Horticulture and Potato Growing, a branch of the Federal State Budgetary Institution Urfanits Ural Branch of the Russian Academy of Sciences, breeding work was carried out to improve the assortment of pears for the Ural region. As a result of many years of breeding work, the range of fruit and berry plants was replenished with a new pear variety, Favoritka, which in 2022 was included in the State Register of Breeding Achievements approved for use. In the process of breeding work, the winter hardiness of pear varieties in the harsh climatic conditions of the Chelyabinsk region was studied, as a result it was noted that infield conditions when the temperature dropped to -40 ° C, freezing of trees of local varieties did not exceed 1 point. An assessment was made of the yield of local varieties, among which the following varieties stand out: Vekovaya, Myth, Favoritka, and Zolotoy Shar, with an average yield of 24 - 28 kg per tree. The economic indicators of the Favoritka pear variety (profitability level of 253.5%) indicate its suitability for cultivation in both industrial and amateur gardening in the Ural region. A pomological description and assessment of the economic usefulness of the new Favoritka pear variety are presented, which combines large fruit (fruit weight can reach 340 g), high winter hardiness, productivity, resistance to abiotic and biotic stressors (not affected by scab, resistant to pear gall mite), has fruits of excellent taste, suitable for fresh consumption, as well as for processing (preparing jams, preserves, compotes, etc.). The variety is in demand among the population and is of interest as a source of giant fruit in further breeding work.

Caracterização das propriedades do estado fresco e endurecido de grautes utilizados em alvenaria estrutural

Abstract Grout is a material usually applied to enhance the mechanical properties of structural masonry. As such, the demand for grout has been growing parallel to the demand for structural masonry. Without guidelines for grout mixing design, these products are often prepared on-site based on the same concepts used for preparing ordinary Portland cement-based concretes. Several grout properties still need to be investigated and understood due to this mixing-design approach, and consequently, the production of ecoefficient grouts is a secondary priority. Due to these obstacles, there is a demand for technical-scientific studies to aid with developing grout design guidelines. This work evaluates the rheological and hardened properties of grout compositions that simulate in-field conditions to show the inadequacy of the mixing design method and a way to understand this lack in the technology. The research investigates how the changes in the water-to-cement ratio, to increase the strength, would affect the fresh and hardened state properties of grouts for structural masonry. The grout’s mixing was done in a rheometer which made it possible to determine the rheological behaviour and parameters during mixing and under different shear conditions. Compressive strength, porosity, and air-permeability were evaluated in the hardened state. The results showed that compositions with more cement content does not necessarily reflect enhanced mechanical properties since the differences were not statistically significant, because other variables were also changed. The research findings suggest that the design method used in practice may not be appropriate and potentially result in the waste of cementitious materials and no-eco-friendly compositions.

Conduction mechanism of Gd2O3 induced by CO2 under in-field conditions

This work investigates the conduction mechanism of hydrothermally grown Gd2O3-sensitive material in order to explain its electrical resistance behaviour when exposed to increasing concentrations of CO2 under in-field conditions. To achieve this, the experimental investigation began with X-ray photoelectron spectroscopy of the Gd2O3 microstructure to verify the oxidation states of the surface. Subsequently, the impact of constant atmospheric factors such as oxygen and relative humidity on the electrical resistance of the Gd2O3 layer was examined. Finally, a progressive dosing of CO2 concentrations ranging from 400 to 3000 ppm was conducted. The DC electrical resistance measurements were performed using a computer-controlled Gas Mixing System operated under a dynamic gas flow regime. Experimental data was validated using the Boltzmann distribution statistics and the grain-to-grain Schottky barrier model. The results highlight the preservation of the n-type semiconductor behaviour of Gd2O3 irrespective of the background relative humidity and bring the oxidising character of CO2 to the fore.

Laser-based remote detection of leaf wetness

Pesticide-free agricultural strategies need new tools for disease prevention. Better than early detection of disease, detection of conditions favorable to their appearance can be a progress. In the case of fungal diseases, the presence of water on the plant surface is necessary. In order to detect remotely this presence early and at the scale of a crop field, we propose a low-cost solution based on laser reflection. Here, experimental results in a controlled environment are presented on both hydrophobic and hydrophilic leaves (rapeseed Brassica Napus and grapevine Vitis Vinifera, respectively). We first assess the water detection on a leaf surface by recreating the dew formation process. We next evaluate the influence of the scanning measurement and leaf inclination on the detection to get closer to in-field conditions. Results show that this method is very sensitive on both types of leaves. Water detection is possible from a low surface coverage with a high temporal precision at 1 m. In the hydrophobic case, water on a leaf surface leads to an increase of the detected signal up to three times compared to a dry leaf. The corresponding minimum surface coverage detectable at 1 m is evaluated at 1.6% thanks to 2D ray-tracing numerical simulations. In the hydrophilic case, on the contrary, water on a leaf surface leads to a decrease of the detected signal by almost half. For both types, the dew detection delay is contained under 5 min and can be improved. Finally, the presented results pave the way to a field application.

Effect of laser wavelength on soil carbon measurements using laser-induced breakdown spectroscopy.

We investigate the effect of laser wavelength on laser-induced breakdown spectroscopy (LIBS) on the measurement of carbon in agricultural soils. Two laser wavelengths, 1064 nm and 532 nm, were used to determine soil carbon concentration. No chemical pretreatment, grinding, or pelletization was performed on soil samples to simulate in-field conditions. A multivariate calibration model with outlier filtering and optimized parameters in partial least squared regression (PLSR) was established and validated. The calibration model estimated carbon content in soils with an average prediction error of 4.7% at a laser wavelength of 1064 nm and 2.7% at 532 nm. The limit of detection (LOD) range for 532 nm was 0.34-0.5 w/w%, approximately half of the LOD range for 1064 nm laser wavelength. The improvement in prediction error and LOD of LIBS measurements is attributed to the increase in plasma density achieved at 532 nm.

On kids' environmental wellbeing and their access to nature in urban heat islands: Hyperlocal microclimate analysis via surveys, modelling, and wearable sensing in urban playgrounds

The aim of this research is to investigate the environmental wellbeing of children in urban outdoor environments by developing and testing a new wearable device called the Baby c-air. Children are particularly vulnerable to environmental discomfort due to their physiological characteristics and lack of awareness about their own adaptation capabilities. This vulnerability can lead to childhood diseases and health issues, especially when exposed to overheating or continuous pollutants. Portable monitoring devices, such as the Baby c-air, can assess children's environmental exposure and provide timely information to limit their health risks.The study involved testing two prototypes of the Baby c-air under laboratory and in-field conditions to verify the accuracy of the device in collecting data. An experimental campaign involving 122 children was conducted in Italy during the summer, across four playgrounds. The option of integrating the COMFA-kid model for thermal comfort assessment was evaluated. The results indicated that microclimate peculiarities underline the importance of a human-centric approach for properly addressing environmental exposure. The discrepancies between thermal sensations provided by interviewed parents/tutors and predicted thermal sensations derived by the COMFA-kid model suggest that adults are generally weakly aware of children's thermal conditions.The Baby c-air can support children's adaptation potential and drive accompanying persons towards implementing conscious behaviors or moving to those areas with better environmental quality. The outcomes of this study can contribute towards urban outdoor design guidelines to improve children's well-being.

PV Based Automatic Irrigation System

Pakistan is an agricultural country and requires an adequate supply of water for irrigation throughout the year. Water is one of the most precious natural resources and its effectual management is a main concern in various agricultural systems around the world. The major problem is the water accumulation by the wealthy farmers store water for their own fields and allow water to pass to other farmers after receiving the money. Secondly, most of the time water wastage occurs due to over watering, it is because there is very large area in the fields (in acres) that is very difficult for the famers to supervise all the area. Similarly, sometime there is inadequate water supply, which cause the damage of crops or results in lesser yield on some section of the field. This paper presents solution of the mentioned problems and increasing the hold of Indus River Systems Authority (IRSA) on the irrigation mechanism so that the required quantity of water can only be delivered at the specific time for each field (as per requiring output from sensors grounded in field). The presented system consists of implement of the sensors in each corner of the fields, when the sensor value (in voltage) goes to satisfied number it sends notification to IRSA and if the water level goes to danger level, it will automatically close the gate from where water is released. New water system with electrical control advancements can improve water utilization proficiency, compelling water sparing and diminishing the natural affects. The target of the presented system is to dodge wastage of water and enhance efficiency of irrigation by utilizing a PLC based irrigation framework with the assistance of soil dampness sensors. An automatic control system of gates helps to close or open the gates if the water level in soil reaches a critical value. The motivation behind this work was to create a self-administering water supply framework that works on utilization of a solitary model according to which; the water supply follows a pre-supplied timetable along-with the monitoring of the in-field conditions, prompting a sensible sparing in the measure of water supply. It should likewise be dependable and effectively deployable to work under cruel outside conditions without the requirement for oversight or customary checking. The deployed electronic system can be powered through solar energy. The developed mechanism can make farmers capable of fulfilling their irrigation needs besides the PV based generated extra electricity can be shared or sold to neighbors or water and power Development authority (WAPDA).

Towards automatic insect monitoring on witloof chicory fields using sticky plate image analysis

ContextSticky trap catches of agricultural pests can be employed for early hotspot detection, identification, and estimation of pest presence in greenhouses or in the field. However, manual procedures to produce and analyze catch results require substantial time and effort. As a result, much research has gone into creating efficient techniques for remotely monitoring possible infestations. A considerable number of these studies use Artificial Intelligence (AI) to analyze the acquired data and focus on performance metrics for various model architectures. Less emphasis, however, was devoted to the testing of the trained models to investigate how well they would perform under practical, in-field conditions. ObjectiveIn this study, we showcase an automatic and reliable computational method for monitoring insects in witloof chicory fields, while shifting the focus to the challenges of compiling and using a realistic insect image dataset that contains insects with common taxonomy levels. MethodsTo achieve this, we collected, imaged, and annotated 731 sticky plates - containing 74,616 bounding boxes - to train a YOLOv5 object detection model, concentrating on two pest insects (chicory leaf-miners and wooly aphids) and their two predatory counterparts (ichneumon wasps and grass flies). To better understand the object detection model's actual field performance, it was validated in a practical manner by splitting our image data on the sticky plate level. Results and conclusionsAccording to experimental findings, the average mAP score for all dataset classes was 0.76. For both pest species and their corresponding predators, high mAP values of 0.73 and 0.86 were obtained. Additionally, the model accurately forecasted the presence of pests when presented with unseen sticky plate images from the test set. SignificanceThe findings of this research clarify the feasibility of AI-powered pest monitoring in the field for real-world applications and provide opportunities for implementing pest monitoring in witloof chicory fields with minimal human intervention.

The influence of the synthesis method on Gd2O3 morpho-structural properties and sensitivity to CO2 under in-field conditions

In this study, we report the implications of the synthesis method on Gd2O3 sensitivity to CO2. The rare-earth oxide was prepared by wet chemical co-precipitation and by hydrothermal method. The obtained powders labelled Gd2O3–CoP and Gd2O3-HT were deposited as thick films over commercial Al2O3 substrates provided with Pt electrodes and a back-side heater. Both powders consist of the same crystallographic phase, with a significant difference appearing in selected area electron diffraction patterns, transmission electron microscopy images at higher magnification and X-ray diffraction spectra, with respect to the crystallization degree. The associated role in sensing properties is revealed via electrical resistance variations determined by CO2 concentrations in the range between 400 and 3000 ppm and variable relative humidity between 0 and 50%RH, similar to the in-field atmosphere. The proposed CO2 interaction mechanism is based on phenomenological investigations which highlight the electronic affinity variation as the effect of dipoles induced by the in-field conditions on the Gd2O3 surface.

Comparison of Algorithms for the AI-Based Fault Diagnostic of Cable Joints in MV Networks

Electrical utilities and system operators (SOs) are constantly looking for solutions to problems in the management and control of the power network. For this purpose, SOs are exploring new research fields, which might bring contributions to the power system environment. A clear example is the field of computer science, within which artificial intelligence (AI) has been developed and is being applied to many fields. In power systems, AI could support the fault prediction of cable joints. Despite the availability of many legacy methods described in the literature, fault prediction is still critical, and it needs new solutions. For this purpose, in this paper, the authors made a further step in the evaluation of machine learning methods (ML) for cable joint health assessment. Six ML algorithms have been compared and assessed on a consolidated test scenario. It simulates a distributed measurement system which collects measurements from medium-voltage (MV) cable joints. Typical metrics have been applied to compare the performance of the algorithms. The analysis is then completed considering the actual in-field conditions and the SOs’ requirements. The results demonstrate: (i) the pros and cons of each algorithm; (ii) the best-performing algorithm; (iii) the possible benefits from the implementation of ML algorithms.

Measuring ammonia concentrations by an infrared photo-acoustic multi-gas analyser in an open dairy barn: Repetitions planning strategy

The infrared photoacoustic spectroscopy is a common gas sensing technique used for research activities to perform continuous measurement of gas concentrations. Few research works have investigated how to collect data and obtain reliable measurements in open and semi-open dairy houses for gas concentration estimation.In the present study, measurements of ammonia (NH3) concentrations were carried out in a semi-open free-stall dairy barn by using a commercial photo-acoustic spectroscopy system (INNOVA by LumaSense Technologies A/S, Denmark), widely used for scientific purposes. Several repetitions for each sampling location (SLs) were investigated in in-field conditions to study the variability of the measurement in each repetition. Based on acquired data, one-way analyses of variance (ANOVA) were carried out for different groups of data. The achieved results showed that the measurement strategy depended on the number of repetitions with effect on the variability of each measurement. In detail, the number of repetitions performed had a significant influence on data collection (P < 0.001). From the outcomes of the research, it is recommended to: perform three repetitions, or at most, four repetitions for each SLs; exclude the first repetition from the data analyses because it reduces measurement variability; consider the mean value of the second and third repetitions as the NH3 concentration value determined at each SL; up to four repetitions (that would take a five-minutes acquisition) are recommended because measurement changed in time when a higher number of repetitions were carried out. The measurement design should be planned based on the number of repetitions and the number of SLs in order to perform more than one SL measurement cycle within an hour. Since the measurement cycles are strictly related to the number of SLs in the barn, they depend on the barn typology and dimensions.The application of a specific measurement strategy is valuable to obtain reliable data that could be used in the research activities focused on estimation of gas concentrations for monitoring air quality, improving animal welfare, assessing mitigation strategies, or estimating emissions in open and semi-open free-stall dairy barns.

The impact of the synthesis temperature on SnO2 morphology and sensitivity to CO2 under in-field conditions

The impact of the synthesis temperature on SnO 2 morphology and sensitivity to CO 2 under in-field conditions • SnO 2 is obtained by hydrothermal method, at different synthesis temperatures. • SnO 2 crystalline nanoparticles are faceted, with regular morphologies. • Main crystallographic planes (0 0 1), (1 0 1), (1 1 0) contain oxygen positions. • The sensing properties are evaluated under in-field conditions, RH = 0–50 %. • CO 2 concentration varies between 400 and 5000 ppm CO 2 . This letter highlights the role of synthesis temperature over the morpho-structural properties of SnO 2 . Specific crystalline nanoparticles with quasi-tetragonal and quasi-hexagonal morphologies are faceted, suggesting a high reactivity to atmospheric oxygen. This is a premise for the sensing ability of SnO 2 in detecting CO 2 . The in-field conditions are ensured by dynamic synthetic air flow with variable relative humidity, a wide range of CO 2 concentrations and potential interfering gases at their specific detection limits.

Effects of Phenotypic Variation on Biological Properties of Endophytic Bacteria Bacillus mojavensis PS17.

Simple SummaryMicroorganisms play an important role in agriculture by protecting and stimulating the growth of plants. The phenotypic activities of microbial biological agents (MBA) can change under different environmental conditions. However, to adapt to these harsh conditions, genetic mutations take place in bacteria that are seen phenotypically, which might not be beneficial or less beneficial to the plants. Some adaptative mechanisms used by microorganisms, especially bacteria, to face these environmental factors lead to the appearance of subpopulations with different morphotypes that may be more adapted to survive in stressful conditions. Moreover, in favorable conditions, these subpopulations may become dominant among the overall bacterial population. In this study, Bacillus mojavensis undergoes phase variation when grown in a minimal medium, in which two colonies, opaque (morphotype I) and translucent (morphotype II), were generated. The characteristics of the generated morphotypes were determined and compared with those of their original strain. Overall, the results obtained showed that the phenotypic characteristics of morphotype I statistically differed from morphotype II. This phenomenon may be one of the factors behind the dissimilarities in the results between the laboratory and field data on the application of MBA.The use of microorganism-based products in agricultural practices is gaining more interest as an alternative to chemical methods due to their non-toxic bactericidal and fungicidal properties. Various factors influence the efficacy of the microorganisms used as biological control agents in infield conditions as compared to laboratory conditions due to ecological and physiological aspects. Abiotic factors have been shown to trigger phase variations in bacterial microorganisms as a mechanism for adapting to hostile environments. In this study, we investigated the stability of the morphotype and the effects of phenotypic variation on the biological properties of Bacillus mojavensis strain PS17. B. mojavensis PS17 generated two variants (opaque and translucent) that were given the names morphotype I and II, respectively. The partial sequence of the 16S rRNA gene revealed that both morphotypes belonged to B. mojavensis. BOX and ERIC fingerprinting PCR also showed the same DNA profiles in both morphotypes. The characteristics of morphotype I did not differ from the original strain, while morphotype II showed a lower hydrolytic enzyme activity, phytohormone production, and antagonistic ability against phytopathogenic fungi. Both morphotypes demonstrated endophytic ability in tomato plants. A low growth rate of the strain PS17(II) in a minimal medium was observed in comparison to the PS17(I) strain. Furthermore, the capacity for biocontrol of B. mojavensis PS17(II) was not effective in the suppression of root rot disease in the tomato plants caused by Fusarium oxysporum f. sp. radices-lycopersici stain ZUM2407, compared to B. mojavensis PS17(I), whose inhibition was almost 47.9 ± 1.03% effective.

Antifungal activity of “HO21-F”, a formulation based on Olea europaea plant extract, in honey bees infected with Nosema ceranae

Nosema ceranae is a microsporidium parasite that silently affects honey bees, causing a disease called nosemosis. This parasite produces resistant spores and germinates in the midgut of honey bees, extrudes a polar tubule that injects an infective sporoplasm in the host cell epithelium, proliferates, and produces intestinal disorders that shorten honey bee lifespan. The rapid extension of this disease has been reported to be widespread among adult bees, and treatments are less effective and counterproductive weakening colonies. This work aimed to evaluate the antifungal activity of a prototype formulation based on a non-toxic plant extract (HO21-F) against N. ceranae. In laboratory, honey bees were infected artificially, kept in cages for 17 days and samples were taken at 7 and 14 days post infection (dpi). At the same time, in field conditions we evaluated the therapeutic effect of HO21-F for 28 days in naturally infected colonies. The effectiveness of the treatment has been demonstrated by a reduction of 83.6 % of the infection levels observed in laboratory conditions at concentrations of 0.5 and 1 g/L without affecting the survival rate. Besides, in-field conditions we reported a reduction of 88 % of the infection level at a concentration of 2.5 g/L, obtaining better antifungal effectiveness in comparison to other commercially available treatments.As a result, we observed that the use of HO21-F led to an increase in population size and honey production, both parameters associated with colony strength. The reported antifungal activity of HO21-F against N. ceranae, with a significant control of spore proliferation in worker bees, suggests the promising commercial application use of this product against nosemosis, and it will encourage new research studies to understand the mechanism of action, whether related to the spore-inhibition effect and/or a stimulating effect in natural response of colonies to counteract the disease.

Evaluation of global and continental scale soil maps for southern Africa using selected soil properties

Earth-systems modelling of the critical zone often require soil maps that represent in-field conditions. Some developing regions, such as southern Africa, do not have detailed soil data for all areas and are often reliant on data from global soil maps and data sets. This raises the question of global and regional soil map and soil data accuracy at local levels. Although previous studies have indicated that global soil maps do not always provide an accurate representation of in-field soil conditions, it is not clear how inaccurate these maps and data are for southern Africa. This study assessed the accuracy of widely used global and continental-scale soil maps for southern Africa. The accuracy of the soil maps was assessed by comparing profile and mapped soil data. Three soil maps of global, continental, and regional scale (Harmonized World Soil Database version 1.2, SOTER for southern African, and AfSoilGrids250m) were compared to observation data from two profile data sets (Africa Soil Profile Database and South African Soil Profile Database). Furthermore, maps of selected soil properties of the AfSoilGrids250m rasters were compared to the Harmonized World Soil Database map.Soil properties were statistically compared through Lin’s Concordance Correlation Coefficient, Root Mean Square Error, and Mean Absolute Error. Investigated maps and point data generally correlated poorly and large Root Mean Square Error and Mean Absolute Error values were observed for most of the properties. Of the investigated soil maps, the digital AfSoilGrids250m soil property raster layers provided the most accurate estimate of in-field soil conditions for selected soil properties in the study region.

Machine-Learning Approach to Determine Surface Quality on a Reactor Pressure Vessel (RPV) Steel

Surface quality measures such as roughness, and especially its uncertain character, affect most magnetic non-destructive testing methods and limits their performance in terms of an achievable signal-to-noise ratio and reliability. This paper is primarily focused on an experimental study targeting nuclear reactor materials manufactured from the milling process with various machining parameters to produce varying surface quality conditions to mimic the varying material surface qualities of in-field conditions. From energising a local area electromagnetically, a receiver coil is used to obtain the emitted Barkhausen noise, from which the condition of the material surface can be inspected. Investigations were carried out with the support of machine-learning algorithms, such as Neural Networks (NN) and Classification and Regression Trees (CART), to identify the differences in surface quality. Another challenge often faced is undertaking an analysis with limited experimental data. Other non-destructive methods such as Magnetic Adaptive Testing (MAT) were used to provide data imputation for missing data using other intelligent algorithms. For data reinforcement, data augmentation was used. With more data the problem of ‘the curse of data dimensionality’ is addressed. It demonstrated how both data imputation and augmentation can improve measurement datasets.