Nitrogen content diagnosis of apple trees canopies using hyperspectral reflectance combined with PLS variable extraction and extreme learning machine

Nitrogen(N)is an important mineral element in apple production.Rapid estimation of apple tree N status is helpful for achieving precise N management.The objective of this work was to explore partial least squares(PLS)regression in dimensional reduction of spectral data and build the diagnostic model.The spectral reflectance data were collected from Fuji apple trees with 4 levels of N fertilizer treatment in the Loess Plateau in 2018 and 2019 using an ASD portable spectroradiometer,and leaf total N content was obtained at the same time.The raw spectra were pretreated using Savitzky-Golay(SG)smoothing and a combination of SG and first-order derivative(SG_FD)or second-order derivative(SG_SD).The samples were divided into a calibration dataset and a prediction dataset using SPXY.Based on 4 factors of PLS regression,including latent variables(LVs),X-loading,variable importance in projection(VIP)and regression coefficients(RC),the 6 methods(LVs,X-loading,VIP_01,VIP_02,RC_01 and RC_02)were derived and used for variable extraction,based on which PLS model and ELM model were established.The results indicated that the spectral data processed by SG_FD had the highest signal-to-noise ratio and was selected for subsequent analysis.The amounts of variables extracted by LVs,X-loading,VIP_01,VIP_02,RC_01 and RC_02 were 6,11,18,305,26 and 88,respectively.The method of extracting variables with an RC threshold based on the minimum RMSEP(RC_02)could effectively avoid the omission of effective information.The RC_02 method was recommended for related research which required accurate wavelength information as a variable.The variable extraction method based on LVs generated an ELM model with a simple structure.The prediction results showed that the ELM model outperformed the PLS model.The PLS(LVs)_ELM model was the best;R2P,RMSEP and RPD were 0.837,2.393 and 2.220,respectively.

Definition of candidate Essential Variables for the monitoring of mineral resource exploitation

The practice of raw material extraction has a high impact on the environment and represents a potential threat to the health and thriving of local communities.The concept of Extractive Essential Variables(EEVs)are explored in order to propose variables that can be used to quantify the environmental footprint of mineral extraction.Considering the interdependence of mining activities with social,economic and environmental issues,the variables target the development of monitoring tools for the implementation of the Sustainable Development Goals(SDGs).The identification of EEVs is based on the use of Earth Observation products in the field of mineral resources exploitation.A list of variables is proposed based on three classes of Essential Variables(EVs):installation and exploration phase,mineral extraction,and ore processing.These variables take into account the impacts of mining on the hydrology,land,water resources and the atmosphere of the area subjected to mineral exploitation.One of the variables is implemented as an operational workflow addressing SDG15,“life on land”.The workflow is intended to assess the area of forest ecosystem lost due to the presence of a mining site.Geospatial data on the extent of mining concessions and forest cover are combined using ArcGIS^(TM).The workflow is successively translated into a Unix script to automatize the process of data treatment.The script is developed using the Geospatial Data Abstraction Library(GDAL).The use of a Virtual Laboratory Platform(VLab),a web-service-based access platform,increases the accessibility of data and resources and the re-use of the script.This work is a first attempt to propose a framework of EEVs,derived data workflows,while the underlying methodology,partially based on scientific publications and on personal reasoning,still needs to be tested and,improved based on expertise in the sector.

Temperature-variable high-frequency dynamic modeling of PIN diode

The PIN diode model for high frequency dynamic transient characteristic simulation is important in conducted EMI analysis. The model should take junction temperature into consideration since equipment usually works at a wide range of temperature. In this paper, a temperature-variable high frequency dynamic model for the PIN diode is built, which is based on the Laplace-transform analytical model at constant temperature. The relationship between model parameters and temperature is expressed as temperature functions by analyzing the physical principle of these parameters. A fast recovery power diode MUR1560 is chosen as the test sample and its dynamic performance is tested under inductive load by a temperature chamber experiment, which is used for model parameter extraction and model verification. Results show that the model proposed in this paper is accurate for reverse recovery simulation with relatively small errors at the temperature range from 25 to 120 ℃.