Recursive Filtering for Stochastic Systems With Filter-and-Forward Successive Relays

In this paper,the recursive filtering problem is considered for stochastic systems over filter-and-forward successive relay(FFSR)networks.An FFSR is located between the sensor and the remote filter to forward the measurement.In the successive relay,two cooperative relay nodes are adopted to forward the signals alternatively,thereby existing switching characteristics and inter-relay interferences(IRI).Since the filter-and-forward scheme is employed,the signal received by the relay is retransmitted after it passes through a linear filter.The objective of the paper is to concurrently design optimal recursive filters for FFSR and stochastic systems against switching characteristics and IRI of relays.First,a uniform measurement model is proposed by analyzing the transmission mechanism of FFSR.Then,novel filter structures with switching parameters are constructed for both FFSR and stochastic systems.With the help of the inductive method,filtering error covariances are presented in the form of coupled difference equations.Next,the desired filter gain matrices are further obtained by minimizing the trace of filtering error covariances.Moreover,the stability performance of the filtering algorithm is analyzed where the uniform bound is guaranteed on the filtering error covariance.Finally,the effectiveness of the proposed filtering method over FFSR is verified by a three-order resistance-inductance-capacitance circuit system.

The changes in soil organic carbon stock and quality across a subalpine forest successional series

Soil organic carbon(SOC)affects the function of terrestrial ecosystem and plays a vital role in global carbon cycle.Yet,large uncertainty still existed regarding the changes in SOC stock and quality with forest succession.Here,the stock and quality of SOC at 1-m soil profile were investigated across a subalpine forest series,including shrub,deciduous broad-leaved forest,broadleaf-conifer mixed forest,middle-age coniferous forest and mature coniferous forest,which located at southeast of Tibetan Plateau.The results showed that SOC stock ranged from 9.8 to29.9 kg·m^(-2),and exhibited a hump-shaped response pattern across the forest successional series.The highest and lowest SOC stock was observed in the mixed forest and shrub forest,respectively.The SOC stock had no significant relationships with soil temperature and litter stock,but was positively correlated with wood debris stock.Meanwhile,the average percentages of polysaccharides,lignins,aromatics and aliphatics based on FTIR spectroscopy were 79.89%,0.94%,18.87%and 0.29%,respectively.Furthermore,the percentage of polysaccharides exhibited an increasing pattern across the forest successional series except for the sudden decreasing in the mixed forest,while the proportions of lignins,aromatics and aliphatics exhibited a decreasing pattern across the forest successional series except for the sudden increasing in the mixed forest.Consequently,the humification indices(HIs)were highest in the mixed forest compared to the other four successional stages,which means that the SOC quality in mixed forest was worse than other successional stages.In addition,the SOC stock,recalcitrant fractions and HIs decreased with increasing soil depth,while the polysaccharides exhibited an increasing pattern.These findings demonstrate that the mixed forest had higher SOC stock and worse SOC quality than other successional stages.The high proportion of SOC stock(66%at depth of 20-100 cm)and better SOC quality(lower HIs)indicate that deep soil have tremendous potential to store SOC and needs more attention under global chan ge.

Long-term trends in the abundance and breeding performance in Adélie penguins:the Argentine Ecosystem Monitoring Program

In this work,we report long-term trends in the abundance and breeding performance of Adélie penguins(Pygoscelis adeliae)nesting in three Antarctic colonies(i.e.,at Martin Point,South Orkneys Islands;Stranger Point/Cabo Funes,South Shetland Islands;and Esperanza/Hope Bay in the Antarctic Peninsula)from 1995/96 to 2022/23.Using yearly count data of breeding groups selected,we observed a decline in the number of breeding pairs and chicks in crèche at all colonies studied.However,the magnitude of change was higher at Stranger Point than that in the remaining colonies.Moreover,the index of breeding success,which was calculated as the ratio of chicks in crèche to breeding pairs,exhibited no apparent trend throughout the study period.However,it displayed greater variability at Martin Point compared to the other two colonies under investigation.Although the number of chicks in crèche of Adélie penguins showed a declining pattern,the average breeding performance was similar to that reported in gentoo penguin colonies,specifically,those undergoing a population increase(even in sympatric colonies facing similar local conditions).Consequently,it is plausible to assume a reduction of the over-winter survival as a likely cause of the declining trend observed,at least in the Stranger Point and Esperanza colonies.However,we cannot rule out local effects during the breeding season affecting the Adélie population of Martin Point.

Integrating species and successional classes for wood production in a mixed forest restoration system in a neotropical region

As forests in neotropical regions,particularly in developing countries,are devastated,interventions to restore biodiversity and its ecological functions are needed.Rural producers have thus been encouraged to grow trees for wood production as an economic activity.The objective of this study was to quantify the increment of wood density of four forest species from different successional classes of a mixed system of restoration in a neotropical forest in Brazil.Tree discs were sampled at breast height and analyzed radially by X-ray densitometry to obtain apparent density and basic density.Three trees each of a species from the pioneer,early and late secondary successional stages and of the dominant species in the climax community.The radial profiles indicated increasing density from the pith to bark of trunks,except for some variations due to wood defects and growth.Average density was 0.576 g cm^(-3),0.655 g cm^(-3),0.706 g cm^(-3)and 0.775 g cm^(-3),respectively,for Peltophorum dubium,Schinus terebinthifolius,Cariniana estrellensis and Hymenaea courbaril.Radial profiles indicated higher amplitudes in the apparent densities for slow-growing species.X-ray densitometry generated parameters such as minimum,average and maximum densities,and radial density variations.These parameters are important for understanding the ecological functional role of successional classes of the Atlantic Forest from the Neotropical region.

Leguminosae plants play a key role in affecting soil physical-chemical and biological properties during grassland succession after farmland abandonment in the Loess Plateau,China

Leguminosae are an important part of terrestrial ecosystems and play a key role in promoting soil nutrient cycling and improving soil properties.However,plant composition and species diversity change rapidly during the process of succession,the effect of leguminosae on soil physical-chemical and biological properties is still unclear.This study investigated the changes in the composition of plant community,vegetation characteristics,soil physical-chemical properties,and soil biological properties on five former farmlands in China,which had been abandoned for 0,5,10,18,and 30 a.Results showed that,with successional time,plant community developed from annual plants to perennial plants,the importance of Leguminosae and Asteraceae significantly increased and decreased,respectively,and the importance of grass increased and then decreased,having a maximum value after 5 a of abandonment.Plant diversity indices increased with successional time,and vegetation coverage and above-and below-ground biomass increased significantly with successional time after 5 a of abandonment.Compared with farmland,30 a of abandonment significantly increased soil nutrient content,but total and available phosphorus decreased with successional time.Changes in plant community composition and vegetation characteristics not only change soil properties and improve soil physical-chemical properties,but also regulate soil biological activity,thus affecting soil nutrient cycling.Among these,Leguminosae have the greatest influence on soil properties,and their importance values and community composition are significantly correlated with soil properties.Therefore,this research provides more scientific guidance for selecting plant species to stabilize soil ecosystem of farmland to grassland in the Loess Plateau,China.

Asset specificity and farmers' intergenerational succession willingness of apple management

Understanding the factors behind apple farmers’willingness to pass on the management of their farms to their descendants is crucial to the continuity of apple production.Due to the high specificity of the human capital,physical assets,land assets,and geographical location in apple production,this study used a binary logistic regression and a mediating effect model to explore the impact of asset specificity on farmers’intergenerational succession willingness of apple management(FISWAM)and to examine the mediating effects of loss aversion in the impact of asset specificity on the FISWAM.The results showed that about 18.68%of the respondents expressed willingness to transfer their apple business between generations,and the FISWAM was generally weak.In addition to the negative impact of geographical location specificity(GLS),human capital specificity(HCS),physical assets specificity(PAS),and land assets specificity(LAS)can enhance the FISWAM.Loss aversion plays a partial mediating role in the impact of PAS,LAS,and GLS on the FISWAM.

Group-Based Successive Interference Cancellation for Multi-Antenna NOMA System with Error Propagation

Non-orthogonal multiple access(NOMA)is viewed as a key technique to improve the spectrum efficiency and solve the issue of massive connectivity.However,for power domain NOMA,the required overall transmit power should be increased rapidly with the increasing number of users in order to ensure that the signal-to-interference-plus-noise ratio reaches a predefined threshold.In addition,since the successive interference cancellation(SIC)is adopted,the error propagation would become more serious as the order of SIC increases.Aiming at minimizing the total transmit power and satisfying each user’s service requirement,this paper proposes a novel framework with group-based SIC for the deep integration between power domain NOMA and multi-antenna technology.Based on the proposed framework,a joint optimization of power control and equalizer design is investigated to minimize transmit power consumption for uplink multi-antenna NOMA system with error propagations.Based on the relationship between the equalizer and the transmit power coefficients,the original problem is transformed to a transmit power optimization problem,which is further addressed by a parallel iteration algorithm.It is shown by simulations that,in terms of the total power consumption,the proposed scheme outperforms the conventional OMA and the existing cluster-based NOMA schemes.

Evaluation of restoration success in arid rangelands of Iran based on the variation of ecosystem services

The plantation of non-native species is one of the most expensive ecological restoration measures in arid and semi-arid areas,while its impacts on local communities are largely ignored.This study assessed the rate of change and the dynamic degree of the economic values of ecosystem services related to local conservation(water yield,stocking rate and aesthetic value)and preserving the future(carbon sequestration,soil protection,soil stability and habitat provision)to determine the restoration success of the plantation of non-native species Haloxylon ammodendron(C.A.Mey.)Bunge ex Fenzl(15-and 30-year-old)in parts of arid rangelands of Bardsir region,Kerman Province,Iran.We investigated the impacts of the two plantations on the seven ecosystem services and ecosystem structures(horizontal and vertical structures,vegetation composition and species diversity)based on field sampling and measurements at four sampling sites(i.e.,control,degraded,and 15-and 30-year-old plantation sites)in spring and summer of 2022.The restoration success of the plantation of non-native species was then examined by assessing the rate of change and the dynamic degree of the total economic value of all ecosystem services as well as the rate of change and the dynamic degree of the economic values of ecosystem services for the two groups(local conservation and preserving the future).Although the plantation of non-native species H.ammodendron enormously improved the vertical and horizontal structures of ecosystems,it failed to increase species diversity and richness fully.Further,despite the plantation of non-native species H.ammodendron had significantly increased the economic values of all ecosystem services,it was only quite successful in restoring carbon sequestration.Path analysis showed that plantation age had a significant impact on restoration success directly and indirectly(through changing ecosystem structures and services).The dynamic degree of the economic values of ecosystem services related to local conservation and preserving the future at the 15-and 30-year-old plantation sites indicated that the two plantations successfully restored the ecosystem services related to preserving the future.The presented method can help managers select the best restoration practices and predict their ecological-social success,especially for the plantation of high-risk non-native species in arid and semi-arid areas.

Arbuscular Mycorrhizal Fungal Colonization at Different Succession Stages in Songnen Saline-Alkali Grassland

Arbuscular mycorrhizal(AM)fungi can form symbiosis with 90%of the vascular plants and play important roles in ecosystem.To realize the AM fungal colonization at different succession stages in saline-alkali land and screen AM fungi species with great functions,roots and soil samples were collected from the three succession stages of Songnen saline-alkali grassland.The soil properties and AM fungal colonization were measured,and the fungus distributed extensively in three stages was annotated by sequencing for AML1/AML2 target,subsequently,maize was selected as the host to verify its colonization.The results showed that the soil properties improved with the succession of saline-alkali grassland.The plants’communities of the three stages could be colonized by AM fungi,and the colonization rate of Leymus chinensis(the third stage)ranged from 66.67%to 100%,Puccinellia tenuiflora(the second stage)ranged from 50%to 80%,while the Suaeda glauca(the first stage)was only 35%–60%.Glomeraceae sp1 was identified as the dominant AM fungi species which occurred frequently in the succession of saline-alkali land with the isolation frequency,relative abundance,and importance value of 100%,18.1%,and 59.1%,respectively.The colonization rate of Glomeraceae sp1 in maize ranged from 80%to 87%and similar mycorrhizal characteristics were detected in the roots of P.tenuiflora,S.glauca,and L.chinensis,indicating that Glomeraceae sp1 colonized the samples in the field.The correlation matrix indicated that colonization rate,colonization intensity,and vesicle abundance were closely related to soil conditions most,and they were related significantly to all the soil properties except cellulase activity.Besides,redundancy analysis(RDA)showed that soil properties drove the changes of AM fungal colonization and sporulation.These results will provide theoretical support for realizing the relationship between AM fungal colonization and soil conditions,and also for the exploration of AM fungi species with great functions.

Understorey species distinguish late successional and ancient forests after decades of minimum human intervention: A case study from Slovenia

The main species composition drivers in temperate deciduous forests are environmental conditions, a stand?s age and the site history, e.g., the succession stage and past land use, as well as disturbance regime and current management. We compared plant species diversity and composition in late successional and ancient forests, cooccurring on the same small river island applying species accumulation curves and nonmetric multidimensional scaling, respectively. Given the island?s geomorphological characteristics, we expected these to be very similar before human intervention in the past. The forests experienced differing disturbance regimes in the past, while over the last 30 years, human intervention has been the same and reduced to a minimum. The ancient forest in this study had two major characteristics defining it as old, mature forest: continuity of presence for more than 200years and specific composition. The late successional forest experienced major disturbance in the 20th century and was allowed natural regeneration by bordering on the ancient forest, representing a potential species pool,and by decades of minimum human intervention. Our results showed that, even though there was no difference in species richness, we could still detect differences between the forests, particularly in the abundance and species composition of the understorey, among which geophytes had the most indicative importance. To make our results useful on a broader scale, we composed from the literature a species list of plants indicative for ancient forest and tested its application. These results are important for distinguishing between old and mature secondary stands and particularly for identifying old forest stands, which should be conserved and, in the case of fragmented landscapes, included in a network connecting forest fragments.

User scheduling and power allocation for downlink multi-cell multi-carrier NOMA systems

In Non-Orthogonal Multiple Access(NOMA),the best way to fully exploit the benefits of the system is the efficient resource allocation.For the NOMA power domain,the allocation of power and spectrum require solving the mixed-integer nonlinear programming NP-hard problem.In this paper,we investigate user scheduling and power allocation in Multi-Cell Multi-Carrier NOMA(MCMC-NOMA)networks.To achieve that,we consider Weighted Sum Rate Maximization(WSRM)and Weighted Sum Energy Efficiency Maximization(WSEEM)problems.First,we tackle the problem of user scheduling for fixed power using Fractional Programming(FP),the Lagrange dual method,and the decomposition method.Then,we consider Successive Pseudo-Convex Approximation(SPCA)to deal with the WSRM problem.Finally,for the WSEEM problem,SPCA is utilized to convert the problem into separable scalar problems,which can be parallelly solved.Thus,the Dinkelbach algorithm and constraints relaxation are used to characterize the closed-form solution for power allocation.Extensive simulations have been implemented to show the efficiency of the proposed framework and its superiority over other existing schemes.

Intelligent reflecting surface-assisted cognitive radio-inspired rate-splitting multiple access systems

Intelligent reflecting surface(IRS)has been widely regarded as a promising technology for configuring wireless propagation environments.In this paper,we utilize IRS to assist transmission of a secondary user(SU)in a cognitive radio-inspired rate-splitting multiple access(CR-RSMA)system in which a primary user's(PU's)quality of service(QoS)requirements must be guaranteed.Without introducing intolerable interference to deteriorate the PU's outage performance,the SU conducts rate-splitting to transmit its signal to the base-station through the direct link and IRS reflecting channels.For the IRS-assisted CR-RSMA(IRS-CR-RSMA)scheme,we derive the optimal transmit power allocation,target rate allocation,and successive interference cancellation decoding order to enhance the outage performance of the SU.The closed-form expression for the SU's outage probability achieved by the IRS-CR-RSMA scheme is derived.Various simulation results are presented to clarify the enhanced outage performance achieved by the proposed IRS-CR-RSMA scheme over the CR-RSMA scheme.

邛海大型水生植物时空分布及其退化原因

根据2021年7和12月、2022年5和9月邛海水生植物调查结果,结合文献资料,分析了邛海水生植物种类组成、群落结构和空间分布状况以及退化原因,提出了邛海水生植物恢复的对策建议。邛海湖区有水生植物23种,主要分布在水深2 m内,在湖泊北岸成片分布,湖泊西岸和南岸呈斑块状分布,东岸零星分布,总面积约1.3 km^(2)。水生植物分布面积由1990s前占湖面积的20%左右缩减到目前的不足5%,沉水植物群落结构简单化,浮叶植物和挺水植物分布范围扩张。1998年洪水从海河口倒灌,致使高枧湾水域沉水植被消失;近10年来湖泊运行水位抬升和透明度下降使得邛海水生植物分布面积进一步缩小、种群单一化。需要恢复邛海水位运行的自然节律,减少污染负荷输入改善水体透明度,辅之人工生态修复等措施,逐步恢复邛海水生态系统健康。

水下连续发射弹体干扰特性及发射时序优化

随着对饱和攻击需求的提高,潜艇连续发射过程的发射时序协调控制研究变得迫切而紧要。考虑到弹体间的流体动力干扰是影响安全发射的主要因素,基于重叠网格多自由度仿真技术,针对连续发射的水下弹体开展姿态弹道干扰特性研究。通过分析流场结构发现,以一定攻角发射的弹体形成的发卡形尾涡是造成后续弹体姿态弹道差异的主要原因。根据不同艇速、时间间隔和空间间隔下弹体间的干扰特性建立干扰评价模型。在保证干扰不影响后续弹体的前提下,以最短发射时长为目标,以综合评价函数为约束,基于改进的贪心算法对大筒多弹式布局的水下弹体开展发射时序优化研究,并采用均匀抽样方法验证优化结果准确性。研究结果表明:相对于均匀抽样方法,改进的贪心算法具有相当的计算准确度和更高的计算效率。

衰退企业“临危受命”CEO如何实现业绩反转——基于模糊集定性比较分析

面临衰退威胁的企业往往期望变更C E O以摆脱困境,然而何种战略能帮助继任CEO实现企业业绩反转,现有研究未能给出解答。基于此,本文将权力理论引入研究框架,运用模糊集定性比较分析方法,以2006—2016年变更CEO的民营制造类衰退企业为研究对象,探索了衰退企业继任CEO、董事会之间的权力制衡关系与反转战略的组合匹配对业绩反转的影响,归纳出“董事会主导×防御型”“外部CEO主导×探索型”“内部CEO主导×防御型”三种反转模式,发现了“董事会为主、CEO为辅”和“CEO为主、董事会监督和咨询为辅”两类制衡关系中主导者动机和能力与战略的匹配,是实现业绩反转的关键,支持了新战略领导层之间的互动关系与企业战略导向的匹配会影响反转战略有效性的命题,丰富了衰退企业业绩反转研究的理论视角和研究方法。

2BP-2000型水稻育秧播种机分盘装置研制

针对现有育秧播种机分盘装置生产效率较低、高速作业时易出现卡盘和秧盘输送不连续等问题,该研究设计了一种生产效率不低于2000盘/h的机械气动式自动分盘装置,可快速、准确完成分盘和供盘,适配2BP-2000型水稻育秧播种机高速播种。阐述了分盘装置的基本结构和工作原理,开展分盘、接盘过程分析,确定装置稳定分盘、接盘作业的关键机构与工作参数。分盘稳定性试验结果表明,生产率为1600~2000盘/h时,分盘稳定性不低于98.67%。开展以层叠秧盘数、生产率和秧盘质量为试验因素,以接盘成功率为试验指标的三因素三水平正交旋转组合试验,得到影响接盘成功率的因素主次关系为生产率、层叠秧盘数、秧盘质量,其中生产率、层叠秧盘数对接盘成功率影响显著(P<0.05),秧盘质量对接盘成功率影响不显著(P≥0.05),表明分盘装置对不同质量的秧盘适应性较好,其最优参数组合为:生产率2000盘/h、层叠秧盘数6盘/层、秧盘质量750 g/盘,该条件下分盘装置的接盘成功率均值为98.43%,与预测值仅相差0.29个百分点。研究结果对提高水稻硬盘育秧播种机械化水平具有实用价值。

替罗非班联合直接取栓对急诊急性脑梗死患者血管再通率影响的临床研究

目的:本研究旨在探讨直接取栓联合替罗非班对急诊急性脑梗死患者血管再通率的影响。方法:以收治的103例急诊急性脑梗死为研究对象,采用随机数字表法将其分为对照组(给予直接取栓治疗,51例)和研究组(给予直接取栓联合替罗非班治疗,52例)。统计两组患者穿刺成功到再通时间、住院时间及并发症发生情况,对比两组神经功能、再通血流分级及mRS评分。结果:研究组穿刺成功到再通时间及住院时间均少于对照组(均P<0.05)。治疗后,研究组神经功能评分低于对照组(P<0.05),研究组再通血流分级中的3级高于对照组(P<0.05),研究组再通血流率为94.23%(49/52),对照组再通血流率为75.00%(39/52),研究组再通血流率高于对照组(P<0.05)。治疗后,研究组mRS评分低于对照组(P<0.05),研究组并发症发生率低于对照组(P<0.05)。结论:直接取栓联合替罗非班能够有效提高急诊急性脑梗死患者血管再通率,改善患者预后水平。

以创意思维为核心且个性化培养的地方高校建筑设计课程教学改革

长期以来,我国地方高校建筑学专业偏重于应用型的人才培养模式,在某种程度上忽视了设计创意思维的着重培养和个性化的因人施教。随着建筑设计行业竞争加剧,对建筑学专业人才能力的重点需求转向了创意思维。而行业以团队的运作方式,必然也需求具备其他优势能力的专业人才。为适应行业的需求变化,借鉴心理学中的成功智力学理论,广州大学建筑学专业在建筑设计系列课程教学中,关联整合了不同能力的培养:围绕建筑设计创意思维能力,打通其与分析能力、实践能力之间的关系。同时,有针对性地按照学生个性特质强化培养,并在团队合作整合各人优势能力的过程中,让学生意识到个性化的价值。

希望感提升式心理护理对不孕症患者婚姻质量、希望水平及成功妊娠率的影响

目的:观察希望感提升式心理护理对不孕症患者婚姻质量、希望水平及成功妊娠率的影响。方法:选取郑州大学第一附属医院生殖医学中心收治的156例不孕症患者作为本次研究对象,采集时间为2022年11月-2023年11月,以单双数作为分组标准,将符合标准的患者随机分成观察组与对照组,两组各78例,其中对照组接受临床常规干预,观察组在以上基础联合希望感提升式心理护理,采用焦虑自评量表(SAS)、抑郁自评量表(SDS)、Olson婚姻质量问卷(ENRICH)、Herth希望量表评估两组干预前后负性情绪、婚姻质量、希望水平的变化,并随访统计两组成功妊娠率及住院满意度。结果:干预前两组SAS评分、SDS评分、ENRICH各项目评分、Herth各项目评分比较,差异无统计学意义(P>0.05),干预后两组指标评分均明显改善,且观察组SAS评分、SDS评分均低于对照组,ENRICH各项目评分、Herth各项目评分均高于对照组,差异有统计学意义(t=6.580,5.846,3.877,4.572,8.492,11.423,8.007,7.757;P<0.05);随访计算观察组成功妊娠50例(64.10%),对照组成功妊娠32例(41.03%),两组相比差异有统计学意义(χ^(2)=8.330,P<0.05);统计满意度可知,两组总满意度相比,差异有统计学意义(χ^(2)=4.112,P<0.05)。结论:经研究结果可知,不孕症患者在希望感提升式心理护理联合常规干预下,能显著改善患者心理状态,明显提升其婚姻质量,在改善希望水平的同时还能提高成功妊娠率,对促进妊娠有着良好影响,且患者接受度较高。

基于SPA-GA-SVR模型的土壤水分及温度预测

土壤湿度和温度是影响水文循环和气候变化的重要参数,在农业实践活动和生态平衡中起着重要作用。为及时、准确地监测土壤含水量(Soil Moisture Content,SMC)及温度,提出了一种基于高光谱数据的预测方法。实验数据集来自为期5天的实地测量,所获得的高光谱数据包含大量的噪声及冗余信息,因此首先用Savitzky-Golay卷积平滑对光谱数据进行降噪处理,利用连续投影算法(Successive Projection Algorithm,SPA)提取数据特征波长,然后通过遗传算法(Genetic Algorithm,GA)对支持向量机回归(Support Vector Regression,SVR)的超参数权值和偏置进行优化,构建SPA-GASVR混合算法模型对土壤水分和温度进行预测,并与BP神经网络(Back Propagation Neural Network,BPNN)、SPA-BP、SVR、SPA-SVR、GA-SVR这5种模型的预测性能进行比较。实验结果表明:各模型在土壤湿度低于30%的情况下,表现出的预测能力差异并不显著。但整体上,复合模型相比于单一的神经网络或机器学习模型具有明显的优势,且经过连续投影算法优化的模型进一步的提高其预测能力,最终SPA-GA-SVR算法在各项指标上均优于其他模型,土壤水分预测模型的R^(2)=0.981、RMSE=0.473%,土壤温度预测模型R^(2)=0.963、RMSE=0.883℃。实验证明基于高光谱数据,经过SPA和GA优化的SVR模型能实现对土壤湿度和温度精准的预测。该方法具有一定的应用价值和现实意义,可应用于便携式高光谱仪和无人机上,实现对土壤水分和温度的实时监测,为今后的播种及灌溉提供理论参考。