Using UAV and Multispectral Images to Estimate Peanut Maturity Variability on Irrigated and Rainfed Fields Applying Linear Models and Artificial Neural Networks

Using UAV and multispectral images has contributed to identifying field variability and improving crop management through different data modeling methods. However, knowledge on application of these tools to manage peanut maturity variability is still lacking. Therefore, the objective of this study was to compare and validate linear and multiple linear regression with models using artificial neural networks (ANN) for estimating peanut maturity under irrigated and rainfed conditions. The models were trained (80% dataset) and tested (20% dataset) using results from the 2018 and 2019 growing seasons from irrigated and rainfed fields. In each field, plant reflectance was collected weekly from 90 days after planting using a UAV-mounted multispectral camera. Images were used to develop vegetation indices (VIs). Peanut pods were collected on the same dates as the UAV flights for maturity assessment using the peanut maturity index (PMI). The precision and accuracy of the linear models to estimate PMI using VIs were, in general, greater in irrigated fields with R2 > 0.40 than in rainfed areas, which had a maximum R2 value of 0.21. Multiple linear regressions combining adjusted growing degree days (aGDD) and VIs resulted in decreased RMSE for both irrigated and rainfed conditions and increased R2 in irrigated areas. However, these models did not perform successfully in the test process. On the other hand, ANN models that included VIs and aGDD showed accuracy of R2 = 0.91 in irrigated areas, regardless of using Multilayer Perceptron (MLP; RMSE = 0.062) or Radial Basis Function (RBF; RMSE = 0.065), as well as low tendency (1:1 line). These results indicated that, regardless of the ANN architecture used to predict complex and non-linear variables, peanut maturity can be estimated accurately through models with multiple inputs using VIs and aGDD. Although the accuracy of the MLP or RBF models for irrigated and rainfed areas separately was high, the overall ANN models using both irrigated and rainfed areas can be used to predict peanut maturity with the same precision.

Space weather impact on ground-based technological systems

This review, offered for the first time in the Russian scientific literature, is devoted to various aspects of the problem of the space weather impact on ground-based technological systems. Particular attention is paid to hazards to operation of power transmission lines, railway automation, and pipelines caused by geomagnetically induced currents (GIC) during geomagnetic disturbances. The review provides information on the main characteristics of geomagnetic field variability, on rapid field variations during various space weather mani-festations. The fundamentals of modeling geoelectric field disturbances based on magnetotelluric sounding algorithms are presented. The approaches to the assessment of possible extreme values of GIC are considered. Information about economic effects of space weather and GIC is collected. The current state and prospects of space weather forecasting, risk assessment for technological systems from GIC impact are discussed. While in space geophysics various models for predicting the intensity of magnetic storms and their related geomagnetic disturbances from observations of the interplanetary medium are being actively developed, these models cannot be directly used to predict the intensity and position of GIC since the description of the geomagnetic field variability requires the development of additional models. Revealing the fine structure of fast geomagnetic variations during storms and substorms and their induced GIC bursts appeared to be important not only from a practical point of view, but also for the development of fundamentals of near-Earth space dynamics. Unlike highly specialized papers on geophysical aspects of geomagnetic variations and engineering aspects of the GIC impact on operation of industrial transformers, the review is designed for a wider scientific and technical audience without sacrificing the scientific level of presentation. In other words, the geophysical part of the review is written for engineers, and the engineering part is written for geophysicists. Despite the evident applied orientation of the studies under consideration, they are not limited to purely engineering application of space geophysics results to the calculation of possible risks for technological systems, but also pose a number of fundamental scientific problems

Space weather impact on ground-based technological systems

This review, offered for the first time in the Russian scientific literature, is devoted to various aspects of the problem of the space weather impact on ground-based technological systems. Particular attention is paid to hazards to operation of power transmission lines, railway automation, and pipelines caused by geomagnetically induced currents (GIC) during geomagnetic disturbances. The review provides information on the main characteristics of geomagnetic field variability, on rapid field variations during various space weather mani-festations. The fundamentals of modeling geoelectric field disturbances based on magnetotelluric sounding algorithms are presented. The approaches to the assessment of possible extreme values of GIC are considered. Information about economic effects of space weather and GIC is collected. The current state and prospects of space weather forecasting, risk assessment for technological systems from GIC impact are discussed. While in space geophysics various models for predicting the intensity of magnetic storms and their related geomagnetic disturbances from observations of the interplanetary medium are being actively developed, these models cannot be directly used to predict the intensity and position of GIC since the description of the geomagnetic field variability requires the development of additional models. Revealing the fine structure of fast geomagnetic variations during storms and substorms and their induced GIC bursts appeared to be important not only from a practical point of view, but also for the development of fundamentals of near-Earth space dynamics. Unlike highly specialized papers on geophysical aspects of geomagnetic variations and engineering aspects of the GIC impact on operation of industrial transformers, the review is designed for a wider scientific and technical audience without sacrificing the scientific level of presentation. In other words, the geophysical part of the review is written for engineers, and the engineering part is written for geophysicists. Despite the evident applied orientation of the studies under consideration, they are not limited to purely engineering application of space geophysics results to the calculation of possible risks for technological systems, but also pose a number of fundamental scientific problems

Effects of intra-vineyard variability and soil heterogeneity on vine performance, dry matter and nutrient partitioning

Three vigor zones, identified in a Barbera vineyard by remote sensing at full canopy, were carefully ground-truthed to determine, over 2 years, the relative weight of soil factors in affecting within-field variability, and to investigate vigor zone influence on dry matter (DM) and nutrient partitioning into different vine organs. Regardless of season, high vigor (HV) achieved stronger vine capacity as total vegetative growth and yield while resulting in markedly less ripened fruits than low vigor (LV) vines. PCA analysis carried out on ten different soil and vine variables clearly separated the three vigor levels and the correlation matrix highlighted that the factors mostly contributing to HV were soil depth, soil K and P concentration, total available water, clay fraction and Nleaf concentration. Conversely, sand fraction was the main marker for LV. When annual DM retrieved in clusters, canes, leaves, and shoot clippings was calculated for each vigor level and expressed as content (i.e. kg/ha) there was a general decreasing trend moving from HV to LV. However, when DM partitioned to each organ was given on a relative basis (i.e. percentage over total) results were similar across vigor levels. Similarly, when nutrients were given as content (e.g. kg or g/ha) out of 120 within-vigor combinations (12 nutrients, 2 seasons, 5 organs), 65 showed a significant difference between HV and LV. Conversely, with data expressed on a concentration basis (i.e. % DM) the number of significant differences between the vigor level means fell to 15. The study strengthens the causal link between soil properties and intra-vineyard spatial variability and clarifies that patterns of dry matter and nutrient partitioning to different vine organs are mildly affected by vine vigor when referred on a relative basis.