Irena Rapčan

Leaf Soil-Plant Analysis Development (SPAD) prediction is a crucial measure of plant health and is essential for optimizing indoor plant management. The deep learning methods offer advanced tools for precise evaluations but their adaptation to the heterogeneous indoor plant ecosystem presents distinct challenges. This study assesses how accurately deep neural network (DNN) predicts SPAD values in leaves on indoor plants when compared to well-established machine learning techniques, including Random Forest (RF) and Extreme Gradient Boosting (XGB). The covariates for prediction were based on low-cost multispectral and soil electro-conductivity (EC) sensors, enabling a non-destructive sensing approach. The study also strongly emphasized multicollinearity analysis quantified by the Variance Inflation Factor (VIF) and two independent indices, as well as its effect on prediction accuracy using deep and machine learning methods. DNN resulted in higher accuracy to RF and XGB, also performing better using filtered data after multicollinearity analysis based on the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE) (R² = 0.589, RMSE = 11.68, MAE = 9.52) in comparison to using all input covariates (R² = 0.476, RMSE = 12.90, MAE = 10.94). Overall, DNN was proven as a more accurate prediction method than the conventional machine learning approach for the prediction of leaf SPAD values in indoor plants, despite using heterogenous plant types and input covariates.

While SoilGrids is an important source of soil property data for a wide range of environmental studies worldwide, there is currently an extreme lack of studies evaluating its accuracy against independent ground truth soil sampling data. This study aimed to provide a comprehensive insight into the accuracy of SoilGrids layers for three physical soil properties representing soil texture components (clay, silt, and sand soil contents) using ground truth data in the heterogeneous landscape of Croatia. These ground truth data consisted of 686 soil samples collected within the national project at a 0–30 cm soil depth, representing the most recent official national data available. The main specificity of this study was that SoilGrids was created based on zero soil samples in the study area, according to the ISRIC WoSIS Soil Profile Database, which is very sparse for the wider surroundings of the study area. The accuracy assessment metrics indicated an overall low accuracy of the SoilGrids data compared with the ground truth data in Croatia, with the average coefficient of determination (R²) ranging from 0.039 for silt and sand to 0.267 for clay, while the normalized root-mean-square error (NRMSE) ranged from 0.362 to 2.553. Despite the great value of SoilGrids in a vast range of environmental studies, this study proved that the accuracy of its products is highly dependent on the presence of ground truth data in the study area.

With the emergence of machine learning methods during the past decade, alternatives to conventional geostatistical methods for soil mapping are becoming increasingly more sophisticated. To provide a complete overview of their performance, this study performed cost–benefit analysis of four soil mapping methods based on five criteria: accuracy, processing time, robustness, scalability and applicability. The evaluated methods were ordinary kriging (OK), regression kriging (RK), random forest (RF) and ensemble machine learning (EML) for the prediction of total soil carbon and nitrogen. The results of these mechanisms were objectively standardized using the linear scaling method, and their relative importance was quantified using the analytic hierarchy process (AHP). EML resulted in the highest cost–benefit score of the tested methods, with maximum values of accuracy, robustness and scalability, achieving a 55.6% higher score than the second-ranked RF method. The two geostatistical methods ranked last in the cost–benefit analysis. Despite that, OK could retain its place as the most frequent method for soil mapping in recent studies due to its widespread, user-friendly implementation in GIS software and its univariate character. Further improvement of machine learning methods with regards to computational efficiency could additionally improve their cost–benefit advantage and establish them as the universal standard for soil mapping.

In this study, we propose integrating unmanned aerial systems (UASs) and machine learning classification for suitability prediction of expanding habitats for endangered flora species to prevent further extinction. Remote sensing imaging of the protected steppe-like grassland in Bilje using the DJI P4 Multispectral UAS ensured non-invasive data collection. A total of 129 individual flora units of five endangered flora species, including small pasque flower (Pulsatilla pratensis (L.) Miller ssp. nigricans (Störck) Zämelis), green-winged orchid (Orchis morio (L.)), Hungarian false leopardbane (Doronicum hungaricum Rchb.f.), bloody cranesbill (Geranium sanguineum (L.)) and Hungarian iris (Iris variegate (L.)) were detected and georeferenced. Habitat suitability in the projected area, designated for the expansion of the current area of steppe-like grassland in Bilje, was predicted using the binomial machine learning classification algorithm based on three groups of environmental abiotic criteria: vegetation, soil, and topography. Four machine learning classification methods were evaluated: random forest, XGBoost, neural network, and generalized linear model. The random forest method outperformed the other classification methods for all five flora species and achieved the highest receiver operating characteristic (ROC) values, ranging from 0.809 to 0.999. Soil compaction was the least favorable criterion for the habitat suitability of all five flora species, indicating the need to perform soil tillage operations to potentially enable the expansion of their coverage in the projected area. However, potential habitat suitability was detected for the critically endangered flora species of Hungarian false leopardbane, indicating its habitat-related potential for expanding and preventing further extinction. In addition to the current methods of predicting current coverage and population count of endangered species using UASs, the proposed method could serve as a basis for decision making in nature conservation and land management.

Provedeno je preliminarno poljsko istraživanje na dvije lokacije s ciljem utvrđivanja utjecaja kultivara, inokulacije sjemena i navodnjavanja na poljsko nicanje, broj mahuna po biljci, broj zrna po mahuni, masu 1000 zrna, prinos zrna i...