Comparing parametric and nonparametric approaches for estimating forage availability using remote sensing and climatic datasets.

The monitoring of landslides has a practical application for the prevention of hazards, especially in the case of large deep-seated landslides. Monitoring data are necessary to understand the relationships between movement and triggers, to predict movement, and to establish an early warning system. This paper compares two phenomenological models for the prediction of the movement of the Kostanjek landslide, the largest landslide in the Republic of Croatia. The prediction models are based on a 4-year monitoring data series of landslide movement, groundwater level, and precipitation. The presented models for landslide movement prediction are divided into the model for the prediction of groundwater level from precipitation data and the model for the prediction of landslide velocity from groundwater level data. The statistical techniques used for prediction are multiple linear regression and random forests. For the prediction of groundwater level, 75 variables calculated from precipitation and evapotranspiration data were used, while for the prediction of landslide movement, 10 variables calculated from groundwater level data were used. The prediction results were mutually compared by k-fold cross-validation. The root mean square error analyses of k-fold cross-validation showed that the results obtained from random forests are just slightly better than those from multiple linear regression, in both, the groundwater level and the landslide velocity models, proofing that multiple linear regression has a potential for prediction of landslide movement.

Different modelling approaches for predicting titanium dioxide nanoparticles mobility in intact soil media

In order to accurately predict soil properties, various machine learning (ML) approaches and hybrid models constructed by integrating ML into regression kriging framework were used to predict and map arable land topsoil pH in Henan province, central China. Random forest (RF), cubist (Cu), support vector machine, artificial neural network, multiple linear regression, classification and regression trees (CART) and their hybrid models were compared for pH accuracy prediction. Among all standalone ML models, RF had the best predictive performance, in terms of the metrics employed in this study, followed by Cu, and CART was the worst. Compared with their ML counterparts, hybrid models could improve the accuracy of topsoil pH prediction to various extents. The accuracy improvement of the hybrid models constructed based on the simple ML was much greater than that based on the complex ensemble ML. Except for artificial neural network kriging , there was no significant difference between different hybrid models in the predicted results of topsoil pH. The outputs from the best predictive models showed that weak acidic soils and weak alkaline soils were the dominant arable soils in the study region, accounting for more than 30% and more than 50% of the total arable land area respectively, the topsoil pH of arable land in the north of the study area is generally higher than that in the south. Boruta variable selection revealed that altitude, climatic covariates closely related to soil moisture availability and some soil properties were the most critical factors affecting and controlling the topsoil pH of arable land.

Analytical models based on physical metallurgy are of limited ability to predict the strength of steel due to the complexities of steelmaking. This paper presents the results obtained using Machine Learning procedures to predict the tensile strength of steel rods manufactured in an electric arc furnace. The available dataset includes 5540 observations (tensile tests) and 97 features (fabrication parameters) monitored during the different stages of the process (electric arc furnace, ladle furnace, continuous casting and hot rolling). The following regression algorithms have been implemented: Multiple Linear Regression, K-Nearest Neighbors, Classification and Regression Tree, three Ensemble Methods (Random Forest, Gradient Boosting and Adaboost) and Artificial Neural Networks. The fine-tuned Random Forest, provided an R2 of 0.775 and a mean absolute percentage error of 0.76% in the test dataset. After optimization, the Feature Importance and the Permutation Importance algorithms showed that chemical variables have the greater influence on the material strength. The quantitative influence of these variables was represented through Partial Dependence Plots. In short, this research has enabled validating a series of Machine Learning models that provide the necessary information for a correct decision-making to optimize the strength of the steel rods.

Forest volume is an important information for assessing the economic value and carbon sequestration capacity of forest resources and serves as a key indicator for energy flow and biodiversity. Although remote sensing technology is applied to estimate volume, optical remote sensing data have limitations in capturing forest vertical height information and may suffer from reflectance saturation. While LiDAR data can provide more detailed vertical structural information, they come with high processing costs and limited observation range. Therefore, improving the accuracy of volume estimation through multi-source data fusion has become a crucial challenge and research focus in the field of forest remote sensing. In this study, we integrated Sentinel-2 multispectral data, Resource-3 stereoscopic imagery, UAV-based LiDAR data, and field survey data to quantitatively estimate the forest volume in Saihanwula Nature Reserve, located in Inner Mongolia, China, on the southern part of Daxing’anling Mountains. The study evaluated the performance of multi-source remote sensing features by using recursive feature elimination (RFE) to select the most relevant factors and applied four machine learning models—multiple linear regression (MLR), k-nearest neighbors (kNN), random forest (RF), and gradient boosting regression tree (GBRT)—to develop volume estimation models. The evaluation metrics include the coefficient of determination (R2), root mean square error (RMSE), and relative root mean square error (rRMSE). The results show that (1) forest Canopy Height Model (CHM) data were strongly correlated with forest volume, helping to alleviate the reflectance saturation issues inherent in spectral texture data. The fusion of CHM and spectral data resulted in an improved volume estimation model with R2 = 0.75 and RMSE = 8.16 m3/hm2, highlighting the importance of integrating multi-source canopy height information for more accurate volume estimation. (2) Volume estimation accuracy varied across different tree species. For Betula platyphylla, we obtained R2 = 0.71 and RMSE = 6.96 m3/hm2; for Quercus mongolica, R2 = 0.74 and RMSE = 6.90 m3/hm2; and for Populus davidiana, R2 = 0.51 and RMSE = 9.29 m3/hm2. The total forest volume in the Saihanwula Reserve ranges from 50 to 110 m3/hm2. (3) Among the four machine learning models, GBRT consistently outperformed others in all evaluation metrics, achieving the highest R2 of 0.86, lowest RMSE of 9.69 m3/hm2, and lowest rRMSE of 24.57%, suggesting its potential for forest biomass estimation. In conclusion, accurate estimation of forest volume is critical for evaluating forest management practices and timber resources. While this integrated approach shows promise, its operational application requires further external validation and uncertainty analysis to support policy-relevant decisions. The integration of multi-source remote sensing data provides valuable support for forest resource accounting, economic value assessment, and monitoring dynamic changes in forest ecosystems.

Soil cadmium (Cd) contamination has attracted a great deal of attention because of its detrimental effects on animals and humans. This study aimed to develop and compare the performances of stepwise linear regression (SLR), classification and regression tree (CART) and random forest (RF) models in the prediction and mapping of the spatial distribution of soil Cd and to identify likely sources of Cd accumulation in Fuyang County, eastern China. Soil Cd data from 276 topsoil (0–20 cm) samples were collected and randomly divided into calibration (222 samples) and validation datasets (54 samples). Auxiliary data, including detailed land use information, soil organic matter, soil pH, and topographic data, were incorporated into the models to simulate the soil Cd concentrations and further identify the main factors influencing soil Cd variation. The predictive models for soil Cd concentration exhibited acceptable overall accuracies (72.22% for SLR, 70.37% for CART, and 75.93% for RF). The SLR model exhibited the largest predicted deviation, with a mean error (ME) of 0.074 mg/kg, a mean absolute error (MAE) of 0.160 mg/kg, and a root mean squared error (RMSE) of 0.274 mg/kg, and the RF model produced the results closest to the observed values, with an ME of 0.002 mg/kg, an MAE of 0.132 mg/kg, and an RMSE of 0.198 mg/kg. The RF model also exhibited the greatest R2 value (0.772). The CART model predictions closely followed, with ME, MAE, RMSE, and R2 values of 0.013 mg/kg, 0.154 mg/kg, 0.230 mg/kg and 0.644, respectively. The three prediction maps generally exhibited similar and realistic spatial patterns of soil Cd contamination. The heavily Cd-affected areas were primarily located in the alluvial valley plain of the Fuchun River and its tributaries because of the dramatic industrialization and urbanization processes that have occurred there. The most important variable for explaining high levels of soil Cd accumulation was the presence of metal smelting industries. The good performance of the RF model was attributable to its ability to handle the non-linear and hierarchical relationships between soil Cd and environmental variables. These results confirm that the RF approach is promising for the prediction and spatial distribution mapping of soil Cd at the regional scale.

The objective was to compare estimates of forage mass (FM) determined with a rising plate meter (RPM) with forage mass determined by total collection method. Estimates of FM impact management decisions and give the producer a greater understanding of forage availability for their herd. Traditional methods of FM estimation using a forage ring or quadrat and total collection are labor intensive and time consuming. The RPM tool aims to provide a quicker method of FM estimation without sacrificing accuracy. The reliability of this tool can be impacted by season, species composition, plant growth state, and pasture management. Forage samples were collected from six random locations within both continuous and rotationally grazed systems. The predominant forage species was endophyte-infected tall fescue. A 0.25 m2 forage ring was randomly thrown, then two RPM (Jenquip Manual Platemeter) measurements were collected in the ring, followed by five measurements adjacent to the ring. The RPM determined the compressed sward height (CSH). Subsequently, forage within the ring was hand-clipped at ground level and collected. Samples were dried for 120 h at 55° C to determine forage availability (kg/ha). This process was repeated weekly for 6 wk. Rising plate meter FM was estimated using the equation: kg dry matter (DM)/ha = CSH × 158 + 200. Data were analyzed using the CORR procedure of SAS 9.4. Forage mass estimates from total ring collection method and RPM were weakly correlated in the rotational grazing system (r = 0.26; P = 0.13) and in the continuous grazing system (r = 0.20; P = 0.24). It is important to note that certain sample collection dates had stronger correlations than others. In the rotationally grazed paddocks, FM from RPM were strongly correlated (r ≥ 0.89, P ≤ 0.02) with FM from total ring collection on 6/23/23 and 7/26/23. In the continuously grazed paddocks, FM estimations from RPM were strongly correlated (r ≥ 0.73, P ≤ 0.10) with forage mass from total collection on 7/20/23 and 7/26/23. Variation among the seven RPM readings at each collection site could have contributed to variability. Coefficient of variation ranged from 9 to 48% and averaged 18% for all samples. The inconsistencies in relationship of forage mass determination methods suggests that more variables need to be considered when determining the accuracy of RPM-derived estimates of forage mass of tall fescue.

This study aims to investigate the effect of stocking rate on vegetation cover (VC) and forage mass (FM) of Mediterranean Kermes oak shrublands, and the growth performance of pure hair goat kids ( Capra hircus L.). Two villages that had the same ecological conditions but where the presence of pure hair goats did or did not exceed the grazing capacity were selected specifically within this scope. The birth weight (BW) and the daily live weight gain at 90 days (DLWG at 90 days) of pure hair goat kids in these villages were identified and compared in order to monitor their growth. As a result, there is a very strong positive correlation between the growth performance of goat kids, and VC and FM in these villages (P<0.01). Results indicated that high stocking rate effect forage availability and this situation cause decrease in the growth performance of goat kids. It was concluded that forage availability and stocking rate in grazing plans are points to consider providing sustainable goat farming.

Energy parameter modeling in plug-in hybrid electric vehicles using supervised machine learning approaches

Urbanization processes greatly change urban landscape patterns and the urban thermal environment. Significant multi-scale correlation exists between the land surface temperature (LST) and landscape pattern. Compared with traditional linear regression methods, the regression model based on random forest has the advantages of higher accuracy and better learning ability, and can remove the linear correlation between regression features. Taking Beijing’s metropolitan area as an example, this paper conducted multi-scale relationship analysis between 3D landscape patterns and LST using Pearson Correlation Coefficient (PCC), Multiple Linear Regression and Random Forest Regression (RFR). The results indicated that LST was relatively high in the central area of Beijing, and decreased from the center to the surrounding areas. The interpretation effect of 3D landscape metrics on LST was more obvious than that of the 2D landscape metrics, and 3D landscape diversity and evenness played more important roles than the other metrics in the change of LST. The multi-scale relationship between LST and the landscape pattern was discovered in the fourth ring road of Beijing, the effect of the extent of change on the landscape pattern is greater than that of the grain size change, and the interpretation effect and correlation of landscape metrics on LST increase with the increase in the rectangle size. Impervious surfaces significantly increased the LST, while the impervious surfaces located at low building areas were more likely to increase LST than those located at tall building areas. It seems that increasing the distance between buildings to improve the rate of energy exchange between urban and rural areas can effectively decrease LST. Vegetation and water can effectively reduce LST, but large, clustered and irregularly shaped patches have a better effect on land surface cooling than small and discrete patches. The Coefficients of Rectangle Variation (CORV) power function fitting results of landscape metrics showed that the optimal rectangle size for studying the relationship between the 3D landscape pattern and LST is about 700 m. Our study is useful for future urban planning and provides references to mitigate the daytime urban heat island (UHI) effect.

The adoption of artificial intelligence tools can improve production efficiency in the agroindustry. Our objective was to perform the predictive modeling of carrot yield and quality. The crop was grown in two commercial areas during the summer season in Brazil. The root samples were taken at 200 points with a 30 × 30 m sampling grid at 82 and 116 days after sowing in both areas. The total fresh biomass, aerial part, and root biometry were quantified for previous crop harvesting to measure yield. The quality of the roots was assessed by sub-sampling three carrots by the concentration of total soluble solids (°Brix) and firmness in the laboratory. Vegetation indices were extracted from satellite imagery. The most important variables for the predictive models were selected by principal component analysis and submitted to the Artificial Neural Network (ANN), Random Forest (RF), and Multiple Linear Regression (MLR) algorithms. SAVI and NDVI indices stood out as predictors of crop yield, and the results from the ANN (R2 = 0.68) were superior to the RF (R2 = 0.67) and MLR (R2 = 0.61) models. Carrot quality cannot be modeled by the predictive models in this study; however, it should be explored in future research, including other crop variables.

Student academic performance prediction is a crucial topic in Educational Data Mining (EDM) and Learning Analytics, which can be used to help at-risk students by undertaking timely actions. The given paper is a systematic review of machine learning methods used in this field. It analyzes a range of approaches, starting with interpretable models such as Multiple Linear Regression and Decision Trees to ensemble and deep learning high-performance models such as Random Forest and Neural Networks. The review highlights the central role of feature engineering and is discussing predictors of academic and behavioral data, social-economic and psychological conditions. One of the broad implications of this paper is providing a comparative analysis of these methods with an emphasis on the continuing trade-off between predictive accuracy and model inter-pretability. Moreover, the disconnect between theory and real-world, full-stack deployment systems, which are more and more critical when it comes to actual usability, is also critically discussed in this review. Major gaps in the research, such as excessive use of synthetic data, lack of practical testing, and ethics, are determined. Lastly, the paper presents future directions which include the use of Explainable AI (XAI), federated learning in privacy and creation of real-time adaptive feedback systems

Changes in the timing of plant phenological phases are important proxies in contemporary climate research. However, most of the commonly used traditional phenological observations do not give any coherent spatial information. While consistent spatial data can be obtained from airborne sensors and preprocessed gridded meteorological data, not many studies robustly benefit from these data sources. Therefore, the main aim of this study is to create and evaluate different statistical models for reconstructing, predicting, and improving quality of phenological phases monitoring with the use of satellite and meteorological products. A quality-controlled dataset of the 13 BBCH plant phenophases in Poland was collected for the period 2007–2014. For each phenophase, statistical models were built using the most commonly applied regression-based machine learning techniques, such as multiple linear regression, lasso, principal component regression, generalized boosted models, and random forest. The quality of the models was estimated using a k-fold cross-validation. The obtained results showed varying potential for coupling meteorological derived indices with remote sensing products in terms of phenological modeling; however, application of both data sources improves models’ accuracy from 0.6 to 4.6 day in terms of obtained RMSE. It is shown that a robust prediction of early phenological phases is mostly related to meteorological indices, whereas for autumn phenophases, there is a stronger information signal provided by satellite-derived vegetation metrics. Choosing a specific set of predictors and applying a robust preprocessing procedures is more important for final results than the selection of a particular statistical model. The average RMSE for the best models of all phenophases is 6.3, while the individual RMSE vary seasonally from 3.5 to 10 days. Models give reliable proxy for ground observations with RMSE below 5 days for early spring and late spring phenophases. For other phenophases, RMSE are higher and rise up to 9–10 days in the case of the earliest spring phenophases.

Abstract. In this paper, reanalysis fields from the ECMWF have been statistically downscaled to predict from large-scale atmospheric fields, surface moisture flux and daily precipitation at two observatories (Zaragoza and Tortosa, Ebro Valley, Spain) during the 1961–2001 period. Three types of downscaling models have been built: (i) analogues, (ii) analogues followed by random forests and (iii) analogues followed by multiple linear regression. The inputs consist of data (predictor fields) taken from the ERA-40 reanalysis. The predicted fields are precipitation and surface moisture flux as measured at the two observatories. With the aim to reduce the dimensionality of the problem, the ERA-40 fields have been decomposed using empirical orthogonal functions. Available daily data has been divided into two parts: a training period used to find a group of about 300 analogues to build the downscaling model (1961–1996) and a test period (1997–2001), where models' performance has been assessed using independent data. In the case of surface moisture flux, the models based on analogues followed by random forests do not clearly outperform those built on analogues plus multiple linear regression, while simple averages calculated from the nearest analogues found in the training period, yielded only slightly worse results. In the case of precipitation, the three types of model performed equally. These results suggest that most of the models' downscaling capabilities can be attributed to the analogues-calculation stage.

با برآورد ظرفیت تبادل کاتیونی با استفاده از ویژگی‏های پایه ای و زودیافت خاک می‏توان در وقت و هزینه صرفه‏جویی کرد. هدف این بررسی، مقایسه دو روش رگرسیون درختی و رگرسیون خطی چندگانه در برآورد ظرفیت تبادل کاتیونی (CEC) با استفاده از ویژگی‏هایخاک است. برای این منظور از داده های 106 نمونه خاک UNSODA استفاده شد. جهت برآورد CEC با استفاده از روش‏های رگرسیون درختی و رگرسیون خطی از ویژگی های اجزای بافت خاک،pH، ماده آلی و چگالی ظاهری استفاده شد. کارآیی روش رگرسیون درختی در برابر روش رگرسیون خطی چندگانه در برآورد CEC مقایسه شدند. نتایج نشان داد که در برآورد CEC با استفاده از روش های رگرسیونی تنها ضرایب ماده آلی (183/3) و درصد رس (274/0) که بیشترین همبستگی را با CEC دارند معنی دار شده و مدل رگرسیونی بر اساس این دو پارامتر توسعه یافت. همچنین از میان پارمترهای ورودی در روش رگرسیون درختی تنها پارامترهای ماده آلی و درصد رس در درخت رگرسیون ظاهر شد. روش رگرسیون درختی در دو مجموعه داده صحت سنجی و اعتبار سنجی بر اساس آماره های ارزیابی R2، RMSE، ME و GMER کارآیی بالاتری نسبت به روش های رگرسیونی خطی در برآورد CEC داشت. از میان روش های رگرسیونی خطی، مدل پیشنهادی کارآیی بالاتری نسبت به مدل های بل و ونکولن و بروسما و همکاران داشت.