Estimation of biomass in wheat using random forest regression algorithm and remote sensing data

Wheat biomass can be estimated using appropriate spectral vegetation indices.However,the accuracy of estimation should be further improved for on-farm crop management.Previous studies focused on developing vegetation indices,however limited research exists on modeling algorithms.The emerging Random Forest(RF) machine-learning algorithm is regarded as one of the most precise prediction methods for regression modeling.The objectives of this study were to(1) investigate the applicability of the RF regression algorithm for remotely estimating wheat biomass,(2) test the performance of the RF regression model,and(3) compare the performance of the RF algorithm with support vector regression(SVR) and artificial neural network(ANN) machine-learning algorithms for wheat biomass estimation.Single HJ-CCD images of wheat from test sites in Jiangsu province were obtained during the jointing,booting,and anthesis stages of growth.Fifteen vegetation indices were calculated based on these images.In-situ wheat above-ground dry biomass was measured during the HJ-CCD data acquisition.The results showed that the RF model produced more accurate estimates of wheat biomass than the SVR and ANN models at each stage,and its robustness is as good as SVR but better than ANN.The RF algorithm provides a useful exploratory and predictive tool for estimating wheat biomass on a large scale in Southern China.

Analytical Analysis and Performance Characterization of Brushless Doubly Fed Induction Machines Based on General Air-gap Field Modulation Theory

Air-gap magnetic field modulation has been widely observed in electric machines.In this study,we present an analytical analysis and performance characterization of brushless doubly fed induction machines(BDFIMs)fed by two independent converters from the perspective of air-gap field modulation.The spiral-loop winding is studied in detail as an example to show the generalized workflow that can also be used to analyze other short-circuited rotor winding types,such as nested-loop and multiphase double-layer windings.Magnetic field conversion factors are introduced to characterize the modulation behavior of special rotor windings and facilitate their comparison in terms of cross-coupling capability,average torque,and harmonic content of the air-gap flux density waveforms.The stator magnetomotive force(MMF),rotor MMF,and resultant air-gap MMF are considered,based on which the closed-form inductance formulas are derived,and the torque equation is obtained along with the optimal current angle for maximum torque operation by using the virtual work principle.The design equations are then developed for the initial sizing and geometry scaling of the BDFIMs.Transient finite element analysis and experimental measurements are performed to validate the analysis.

Effects of tillage on soil nitrogen and its components from rice-wheat fields in subtropical regions of China

It is of great significance to explore the effects of different tillage practices on total nitrogen and its components in rice-wheat rotation farmland.The experiment was carried out in Jiangyan County,Jiangsu Province of China,and a total of four treatments were set up:minimum tillage(MT),rotary tillage(RT),conventional tillage(CT),and conventional tillage without straw retention(CT0).The total nitrogen(TN),light fraction nitrogen(LFN),heavy fraction nitrogen(HFN),particulate nitrogen(PN),and mineral-associated nitrogen(MN)in 0-20 cm soil were determined.The results show that MT increased TN concentration by2.26%-27.57%compared with the other treatments in 0-5 cm soil,but it lost this advantage in 5-10 cm and 10-20 cm soil.MT altered the concentration of LFN by 6.03%-95.86%,of HFN by 1.68%-20.75%,of PN by 12.58%-96.83%,and of MN by−1.73%-9.83%as compared to RT,CT,and CT0 in 0-5 cm soil,respectively.With the deepened of soil depth,the concentration of TN,LFN,HFN,PN,and MN decreased quickly in MT,which was lower than that in RT and CT at 10-20 cm soil depth.Straw return increased the concentration of TN and its components in 0-20 cm soil.The concentration of TN was extremely significantly positively correlated with that of LFN,HFN,PN,and MN(p<0.01).The variation of TN was significantly positively correlated with that of LFN,HFN,PN,and MN(p<0.01),and LFN showed the highest sensitivity to tillage practice.In general,minimum tillage combined with straw retention increased the concentration of soil TN and its components in topsoil.LFN was the best indicator to indicate the change in soil total nitrogen affected by tillage practice.

Evaluation of ecosystem service of straw return to soil in a wheat field of China

Crop straw is an important natural resource in China because it is rich in nutrients.When returned to fields after harvests,the straw can improve soil quality and the next crop’s yield.Evaluating the economic values of the main ecological services of a farmland ecosystem while implementing the straw return technique can be a more systematic and comprehensive approach to better understand the contribution of straw return to the development of ecological agriculture.Based on the data of a field experiment established in 2010 with varying numbers of years of straw return,four ecological services,i.e.,agricultural product and industrial raw materials,atmospheric regulation and purification,soil nutrient accumulation,and water conservation,were selected to estimate a net ecosystem service value(ESV)of a wheat field’s ecosystem services.Agro-ecosystem service appraisal theories were applied to estimate the economic value of each service.Results showed that straw returning improved the total ESV in the wheat system.Compared to the no straw return treatment,1 year,3 years,5 years or 7 years of straw returning altered the economic value of the agricultural product and industrial raw materials(EVAIM)by-5.93%to 7.84%and improved atmospheric regulation(EVAR)by 13.66%-30.80%,soil nutrient accumulation(EVSNA)by 59.87%-233.31%and water conservation(EVWC)by 2.60%-13.26%.The total ESV of wheat plots with 1-7 years of straw returning was 3.67%-27.41%higher than that with no straw return,and the total ESV increased with the increase in years of straw return.The proportion of EVAIM out of the total ESV in this wheat field system was highest(accounted for 47.09%-55.64%),followed by EVAR and EVWC.The value of EVSNA was the lowest.However,the proportion of EVSNA was higher than that of water conservation after the fifth year of straw return.In general,the adoption of continuous straw returning in a wheat field ecosystem is ecologically valuable.The results can inform the development and implementation of ecological compensation policies involving straw return.