The article provides an overview of the accuracy of various yield forecasting algorithms and offers a detailed explanation of the models and machine learning algorithms that are required for crop yield forecasting. A unified crop yield forecasting methodology is developed, which can be adjusted by adding new indicators and extensions. The proposed methodology is based on remote sensing data taken from free sources. Experiments were carried out on crops of cereals, legumes, oilseeds and forage crops in eastern Kazakhstan. Data on agricultural lands of the experimental farms were obtained using processed images from Sentinel-2 and Landsat-8 satellites (EO Browser) for the period of 2017–2022. In total, a dataset of 1600 indicators was collected with NDVI and MSAVI indices recorded at a frequency of once a week. Based on the results of this work, it is found that yields can be predicted from NDVI vegetation index data and meteorological data on average temperature, surface soil moisture and wind speed. A machine learning programming language can calculate the relationship between these indicators and build a neural network that predicts yield. The neural network produces predictions based on the constructed data weights, which are corrected using activation function algorithms. As a result of the research, the functions with the highest prediction accuracy during vegetative development for all crops presented in this paper are multi-layer perceptron, with a prediction accuracy of 66% to 99% (85% on average), and polynomial regression, with a prediction accuracy of 63% to 98% (82% on average). Thus, it is shown that the use of machine learning and neural networks for crop yield prediction has advantages over other mathematical modelling techniques. The use of machine learning (neural network) technologies makes it possible to predict crop yields on the basis of relevant data. The individual approach of machine learning to each crop allows for the determination of the optimal learning algorithms to obtain accurate predictions.

Background: Bone elasticity is one of the most important biomechanical parameters of the skeleton. It varies markedly with age, anatomical zone, bone type (cortical or trabecular) and bone marrow status. Methods: This review presents the result of a systematic review and analysis of 495 experimental and analytical papers on the elastic properties of bone tissue. The bone characteristics of hip, shoulder, skull, vertebrae as a function of the factors of age (young and old), sex (male and female), presence/absence of bone marrow and different test methods are examined. The Bayesian neural network (BNN) was used to estimate the uncertainty in some skeletal parameters (age, sex, and body mass index) in predicting bone elastic modulus. Results: It was found that the modulus of elasticity of cortical bone in young people is in the range of 10–30 GPa (depending on the type of bone), and with increasing age, this slightly decreases to 10–25 GPa, while trabecular tissue varies from 0.2 to 5 GPa and reacts more acutely to osteoporosis. Bone marrow, according to several studies, is able to partially increase stiffness under impact loading, but its contribution is minimal under slow deformations. Conclusions: BNN confirmed high variability, supplementing the predictions with confidence intervals and allowed the formation of equations for the calculation of bone tissue elastic modulus for the subsequent selection of the recommended elastic modulus of the finished implant, taking into account the biomechanical characteristics of bone tissue depending on age (young and old), sex (men and women) and anatomical zones of the human skeleton.

The challenges associated with climate change are increasing, so there is an urgent need for modern tools to effectively assess, predict and minimise climate risks. This research paper presents the results of the development of the innovative Community Climate Change Impacts Service (C3IS) system, which represents a paradigm shift in climate risk analysis. C3IS is a module that includes a pioneering set of tools with an interactive application programming interface (API) fully integrated with the Google Earth Engine (GEE) platform. The C3IS module enables lightning-fast collection and visualisation (in real time) of critical climate risk data through flexible integration with GEE. The advantages of this integration are the ability to use the GEE platform to access an extensive petabyte-scale catalogue of geospatial data and an ever-expanding database of satellite imagery. The defining feature of the developed module is accessibility and usability due to the exclusion of operations such as the time-consuming preliminary processing of “big data”; complex modelling; and large-scale data storage. The study shows the promising application of the C3IS module for the operational decision making and development of sound strategies for effective climate change mitigation.

The integration of Earth Remote Sensing (ERS) data with advancements in artificial intelligence has revolutionised sustainable land management. Current research in this field focuses on analysing remotely sensed data. This paper presents the results of effectively using spectral reflectance values of soil samples from several climatic zones in Kazakhstan to classify the content of macronutrients in soil, including nitrogen, phosphorus, potassium, and humus. The analysis of macronutrient content in the soil, combined with spectral data from Sentinel-2 L2A satellite imagery, has been integrated with geoinformation systems and mathematical modelling. The results of the macronutrient classification have been visualised in the form of cartograms. The classification analysis involved mathematical modelling of statistical data arrays on the content of phosphorus, potassium, humus, and nitrogen in the soil using the BN-BPNN neural network model, compared with data obtained from agrochemical soil sampling. The model tests demonstrate high efficiency for two soil types. For chernozem soil, the accuracy of nitrogen determination was 90.55%, phosphorus 98.1%, potassium 57.06%, and humus 90.54%. For chestnut soil, the accuracy was nitrogen 98.19%, phosphorus 42.16%, potassium 89.81%, and humus 98.88%. These results highlight the significant potential of this methodology for adaptation to various soil and climatic conditions. The “smart” technique developed for remote determination of macronutrient content, with automated express construction of cartograms, provides real-time information on soil nutrient levels. This research significantly enhances the integration efficiency of RS (remote sensing), GIS (geographical information systems), and AI (artificial intelligence) data in agriculture, contributing to sustainable land management.

The reconstruction of segmental bone defects requires patient-specific scaffolds that combine mechanical safety, biological functionality, and rapid manufacturing. We converted CT-derived mandibular geometry into a functionally graded Ti-6Al-4V lattice and optimised porosity, screw layout, and strut thickness through a cyber-physical loop that joins high-fidelity FEM, millisecond ANN, and a BN for uncertainty quantification. Fifteen candidate scaffolds were fabricated by direct metal laser sintering and hot isostatic pressing and were mechanically tested. FEM predicted stress and stiffness with 98% accuracy; the ANN reproduced these outputs with 94% fidelity while evaluating 10,000 designs in real time, and the BN limited failure probability to <3% under worst-case loads. The selected 55–65% porosity design reduced titanium use by 15%, shortened development time by 25% and raised multi-objective optimisation efficiency by 20% relative to a solid-plate baseline, while resisting a 600 N bite with a peak von Mises stress of 225 MPa and micromotion < 150 µm. Integrating physics-based simulation, AI speed, and probabilistic rigour yields a validated, additively manufactured scaffold that meets surgical timelines and biomechanical requirements, offering a transferable blueprint for functional scaffolds in bone and joint surgery.