Developing data-driven models for quantifying Cochlodinium polykrikoides using the Geostationary Ocean Color Imager (GOCI)

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.

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.

Potential inhibition of the harmful dinoflagellate Cochlodinium (= Margalefidinium) polykrikoides by the intrusion of Changjiang diluted water into Korea coastal waters

Eğitim, her birey ve bir bütün olarak toplum için ekonomik, sosyal ve kültürel gelişimin temelidir. Ülkemizde orta öğretim kurumlarına Milli Eğitim Bakanlığı tarafından yapılan lise giriş sınavı ile öğrenci kabul edilmektedir. Bu çalışmada, 2019 yılında Türkiye'nin 81 ilinde lise giriş sınavına giren öğrencilerin başarı oranları makine öğrenimi regresyon ve beta regresyon modeli ile ele alınmıştır. Bu makale, boşanma oranı, gayri safi yurtiçi hasıla, okuma yazma bilmeyenlerin sayısı ve yüksek öğretim nüfusu sayısı gibi değişkenleri kullanarak öğrencilerin başarı oranlarını modellemeyi, tahmin etmeyi ve açıklamayı amaçlamaktadır. Başarı oranlarını tahmin etmek için destek vektörü regresyon, rastgele orman, karar ağacı ve beta regresyon modeli uygulanmıştır. En yüksek R2 değerine sahip iki modelin beta regresyon ve rastgele orman modelleri olduğu bulunmuştur. Beta regresyon ve rastgele orman modelinin tahmin hataları incelendiğinde, başarı oranlarını tahmin etmede rastgele orman modelinin beta regresyon modeline göre nispeten üstün olduğu görülmektedir. Beta regresyon modeli Çanakkale ilinin başarı oranlarının en iyi yordayıcısı iken, rastgele orman modeli Ankara'nın başarı oranlarını iyi tahmin etmiştir. Ayrıca beta regresyon modelinde başarı oranları için anlamlı bulunan değişkenlerin rastgele orman modelinde de önemli olduğu görülmüştür. Öğrencilerin başarı oranlarını tahmin etmek için hem beta hem de rastgele orman modellerinin kullanılması önerilir.

Phaeocystis antarctica unusual summer bloom in stratified antarctic coastal waters (Terra Nova Bay, Ross Sea)

Three-dimensional digital soil mapping of multiple soil properties at a field-scale using regression kriging

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

Accurate estimation of forage availability is crucial for effective rangeland management. This study, conducted in a hot semi-arid rangeland (844.7 ha) in Khuzestan province, Iran, outlines a three-step approach to achieve this goal. Forage availability was measured using the cutting and weighing method on 58 one-square-meter sample plots. Initially, remote sensing (Sentinel-2) and climatic indicators were prepared, and the Pearson correlation coefficient was employed to analyze relationships between these independent variables and the dependent variable (forage mass). The second step focused on identifying optimal vegetation indices for forage availability estimation using multiple linear regression (MLR), Random Forest (RF), and classification and regression trees (C&RT) algorithms. The third step aimed to enhance model performance by integrating vegetation and climatic indices. Using 58 sample plots, 30 were used for modeling and 28 exclusively for final validation. A k-fold cross-validation (k = 5) was employed, with 47 plots for training and 11 for validation in each iteration. Model performance (MLR, RF, C&RT) was evaluated using average R2 and RMSE metrics from all validation folds, ensuring robust and reliable results. The Random Forest used an internal 60-20-20 split. Correlation analysis revealed that MSAVI2 (-0.83), SAVI (-0.23), DVI (-0.17), potential evapotranspiration index (-0.42), and Transou index (0.35) were the most significant variables. In the second step, R2 values for MLR, RF, and C&RT models were 0.54, 0.54, and 0.68, respectively. Incorporating potential evapotranspiration and Transou indices into the models boosted their coefficients of determination to 0.68, 0.72, and 0.91, with corresponding RMSE reductions of 85%, 69%, and 22%. The study concludes that a combination of the MSAVI2 index with potential evapotranspiration and Transou indices, implemented through the non-parametric C&RT regression, offers a robust method for estimating rangeland forage availability in hot, semi-arid, and arid environments.

Population data is crucial for policy decisions, but fine-scale population numbers are often lacking due to the challenge of sharing sensitive data. Different approaches, such as the use of the Random Forest (RF) model, have been used to disaggregate census data from higher administrative units to small area scales. A major limitation of the RF model is its inability to quantify the uncertainties associated with the predicted populations, which can be important for policy decisions. In this study, we applied a Bayesian Additive Regression Tree (BART) model for population disaggregation and compared the result with a RF model using both simulated data and the 2021 census data for Ghana. The BART model consistently outperforms the RF model in out-of-sample predictions for all metrics, such as bias, mean squared error (MSE), and root mean squared error (RMSE). The BART model also addresses the limitations of the RF model by providing uncertainty estimates around the predicted population, which is often lacking with the RF model. Overall, the study demonstrates the superiority of the BART model over the RF model in disaggregating population data and highlights its potential for gridded population estimates.

This article demonstrates a successful application of fluorescence line height (FLH) images from the Medium Resolution Imaging Spectrometer (MERIS) and Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagers and provides a strong argument for making more widespread use of FLH in monitoring surface phytoplankton in coastal waters. In the present example, MERIS and MODIS FLH images show the start of the spring bloom in coastal waters of the Strait of Georgia in British Columbia, Canada. The images clearly show a recurring pattern in five of the eight years from 2003 to 2010 covered by MERIS, which suggests seeding of the early spring bloom from narrow coastal inlets. Such seeding has been suggested before, but never observed. FLH images show the blooms more clearly than images of surface chlorophyll based on the ratios of water-leaving radiances in the blue and green spectral range (440–560 nm). FLH images used here have been derived with no atmospheric correction. Alternative products based on the blue/green ratio require atmospheric correction, which is difficult in coastal areas. Such products also tend to be more significantly confused with other constituents of coastal waters.

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.

Accurate reconstruction of photosynthetically active radiation (PAR) in aquatic environments is critical for understanding primary production and ecosystem dynamics. This study evaluates the generalization abilities of artificial neural networks (ANNs) for location-independent PAR reconstruction using data from BGC-Argo floats. The proposed ANN model is trained on datasets from multiple geographic regions and validated against independent test data from diverse oceanic locations. Comparisons with multiple linear regression (MLR) and regression tree (RT) models demonstrate that the ANN consistently achieves superior predictive accuracy, with R² values exceeding 0.97 in most test cases. The results indicate that neural networks can effectively generalize across different marine environments, even in regions with distinct optical properties. Notably, the ANN outperforms alternative models except in one test case, highlighting the potential influence of regional environmental factors. This study underscores the potential of machine learning techniques to enhance bio-optical sensor configurations and reduce the necessity for dedicated PAR sensors.

Introducing two Random Forest based methods for cloud detection in remote sensing images

Knowledge about phytoplankton composition is important for biological and biogeochemical research as well as for ecological applications (e.g., water quality) in coastal and inland waters. Satellite remote sensing can potentially map the baseline patterns, anomalies, and trends of phytoplankton composition on a synoptic basis. A prominent challenge is the attribution of the total optical signal to phytoplankton amid interference from minerals and humus. Here, we obtained the phytoplankton light absorption coefficient, aph(λ), in the Chesapeake Bay by partitioning satellite‐derived total light absorption coefficient of water using the generalized stacked‐constraints model (GSCM). We show that the red‐to‐blue band ratio of GSCM‐derived aph(670)/aph(440) can be associated with diatom fraction in Chesapeake Bay. Further, the spatial‐temporal patterns shown in the satellite‐derived diatom fraction data agree well with field studies conducted previously around this region, including low diatom dominance in summer, high diatom dominance in the lower bay in winter, diatom‐dominated spring blooms in coastal waters outside of the bay, and increasing seasonal variability of diatom fraction from the upper to the lower bay. We also found that in the middle bay the summer diatom fraction correlates strongly with spring streamflow on an annual basis, which can be explained because sediment deposited by spring freshets is the main source of silicate supply during summer. These results suggest that the satellite‐derived diatom fraction maps can serve as a baseline for detecting phytoplankton composition anomalies, and highlight the effectiveness of using absorption‐based approach to extract phytoplankton composition information for optically complex waters.

This paper contributes to the ongoing debate over Likert scale experiments, in particular the issues of how to treat acceptability judgment data (as ordinal or interval) and what statistical model is appropriate to apply. We analyze empirical data on native speakers’ intuitions regarding marginal change-of state verbs in Russian (e.g. ukonkretit’ ‘concretize’, ovnešnit’ ‘externalize’) and compare the outcomes of five statistical models (parametric and non-parametric tests): (1) ANOVA; (2) Ordinal Logistic Regression Model; (3) Mixed-Effects Regression Model for Ordinal data; (4) Regression Tree and Random Forests Model; and (5) Classification Tree and Random Forests Model. We make four claims: (1) all five models are appropriate for this data to a greater or lesser degree; (2) overall, the outcomes of parametric and non-parametric tests applied to this data provide comparable results; (3) Classification Tree and Random Forests Model is the most appropriate, informative, and user-friendly regarding this data; and (4) the use of a culturally entrenched grading scale is an advantage.