Construction of Predictive Models to Describe Apparent and Complex Viscosity Values of O/W Model System Meat Emulsions Using Adaptive Neuro – Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN)

This paper introduces an adaptive neuro ?C fuzzy inference system (ANFIS) and artificial neural networks (ANN) models to predict the apparent and complex viscosity values of model system meat emulsions. Constructed models were compared with multiple linear regression (MLR) modeling based on their estimation performance. The root mean square error (RMSE), mean absolute error (MAE) and determination coefficient (R ²) statistics were performed to evaluate the accuracy of the models tested. Comparison of the models showed that the ANFIS model performed better than the ANN and MLR models to estimate the apparent and complex viscosity values of the model system meat emulsions. Coefficients of determination (R ²) calculated for estimation performance of ANFIS modeling to predict apparent and complex viscosity of the emulsions were 0.996 and 0.992, respectively. Similar R ² values (0.991 and 0.985) were obtained when estimating the performance of the ANN model. In the present study, use of the constructed ANFIS models can be suggested to effectively predict the apparent and complex viscosity values of model system meat emulsions.     

Inclusion of fractal dimension in four machine learning algorithms improves the prediction accuracy of mean weight diameter of soil

The study of soil mean weight diameter (MWD), essential for sustainable soil management, has recently received much attention. As the estimation of MWD is challenging, labor-intensive, and time-consuming, there is a crucial need to develop a predictive estimation method to generate helpful information required for the soil health assessment to save time and cost involved in soil analysis. Pedotransfer functions (PTFs) are used to estimate parameters that are ‘difficult to measure’ and time-consuming with the help of ’easy to measure’ parameters. In the current study, empirical PTFs, i.e., multi-linear regression (MLR), and four machine learning based PTFs, i.e., artificial neural network (ANN), support vector machine (SVM), classification and regression trees (CART), and random forest (RF) were used for mean weight diameter prediction in Karnal district of Haryana, India. A total of 121 soil samples from 0‐15 and 15‐30 cm soil depths were collected from seventeen villages of Nilokheri, Nissing, and Assandh blocks of Karnal district. Soil parameters such as bulk density (BD), fractal dimension (D), soil texture (i.e., sand, silt, and clay), organic carbon (OC), and glomalin content were used as the input variables. Two input combinations, i.e., one with texture data (dataset 1) and the other with fractal dimension data replacing texture (dataset 2), were used, and the complete dataset (121) was divided into training and testing datasets in a 4:1 ratio. The model performance was evaluated by statistical parameters such as mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), normalized root mean square error (NRMSE), and determination coefficient (R²). The comparison results showed that including the fractal dimension in the input dataset improved the prediction capability of ANN, SVM, and RF. MLR and CART showed lower predictive ability than the other three approaches (i.e., ANN, SVM, and RF). In the training dataset, RMSE (mm) for the SVM model was 8.33% lower with D than with texture as the input, whereas, in the testing dataset, it was 16.67% lower. Because SVM is more flexible and effectively captures non-linear relationships, it performed better than the other models in predicting MWD. As seen in this study, the SVM model with input data D is the best in its class and has a high potential for MWD prediction in the Karnal district of Haryana, India.     

基于混合效应的大别山地区杉木树高-胸径模型比较

基于安徽省大别山区马鬃岭林场杉木人工林30块样地1087组数据,选用7个常用树高-胸径(H-D)模型(线性模型、Chapman-Richards模型、Logistic模型等),采用最小二乘法拟合并选出最优基础模型(式11,只含D变量的Chapman-Richards模型),然后基于该模型构建含林分变量优势木平均高度、密度的H-D模型(式12),同时考虑样地水平的随机效应,分别基于式11、12构建混合模型(式13、14),并用幂函数、指数函数消除误差异方差,利用决定系数(R²)、均方根误差(RMSE)、平均绝对误差(MAE)和平均相对误差绝对值(MAPE)等指标来评价模型的拟合与预测能力,最终获取最优树高预测模型.结果表明:含林分变量的模型的拟合精度(式12,R²=0.863、RMSE=1.381、MAE=0.971)优于基础模型(式11,R²=0.827、RMSE=1.554、MAE=0.101).对于误差方差,幂函数、指数函数均能较好地消除异方差,但幂函数相对最好.混合模型的拟合与预测能力均优于式11、12,但混合模型(式13、14)之间的拟合与预测精度相差不大.基于混合效应的H-D模型(式13)能够较好地描述不同林分间H-D关系的差异,实际运用中可选用该模型来预测杉木树高,具有较高的预测精度.     

不同地形条件下植被盖度信息提取技术研究

为系统地研究特定区域的植被盖度信息提取技术, 在不同的地形条件下, 比较了目前流行的多种高光谱遥感植被盖度提取方法。结果表明: 最优高光谱归一化植被指数(NDVI₁)的建模和验证精度均高于其他两种归一化植被指数(NDVI), 直接采用NDVI建立的回归模型对研究区植被盖度的估测能力低于像元二分模型; 阴坡的最佳模型为基于一阶微分的偏最小二乘回归模型(PLSR模型), 其建模决定系数(R²)为0.810, 均方根误差(RMSE)为6.29, 验证R²为0.773, RMSE为8.85; 阳坡的最佳模型为基于二阶微分的PLSR模型, 其建模R²为0.823, RMSE为6.04, 验证R²为0.801, RMSE为7.35; 平原的最佳模型为全受限的线性光谱混合分解模型(FCLS), 其验证R²为0.852, RMSE为5.86。     

林地叶面积指数遥感估算方法适用分析

叶面积指数是与森林冠层能量和CO2交换密切相关的一个重要植被结构参数,为了探讨估算林地叶面积指数LAI的遥感适用方法和提高精度的途径,利用TRAC仪器测定北京城区森林样地的LAI,从Landsat TM遥感图像计算NDVI、SR、RSR、SAVI植被指数,分别建立估算LAI的单植被指数统计模型、多植被指数组合的改进BP神经网络,获取最有效描述LAI与植被指数非线性关系的方法并应用到TM图像估算北京城区LAI。结果表明,单植被指数非线性统计模型估算LAI的精度高于线性统计模型;多植被指数组合神经网络中,以NDVI、RSR、SAVI组合估算LAI的精度最高,估算值与观测值线性回归方程的R2最高,为0.827,而RMSE最低,为0.189,神经网络解决了多植被指数组合统计模型非线性回归方程的系数较多、较难确定的问题,可较为有效的应用于遥感图像林地LAI的估算。     

Simulation of PSII-operating efficiency from chlorophyll fluorescence in response to light and temperature in chrysanthemum (<Emphasis Type="Italic">Dendranthema grandiflora</Emphasis>) using a multilayer leaf model

Chlorophyll fluorescence serves as a proxy photosynthesis measure under different climatic conditions. The objective of the study was to predict PSII quantum yield using greenhouse microclimate data to monitor plant conditions under various climates. Multilayer leaf model was applied to model fluorescence emission from actinic light-adapted (F') leaves, maximum fluorescence from light-adapted (Fm') leaves, PSII-operating efficiency (F_q'/F_m'), and electron transport rate (ETR). A linear function was used to approximate F' from several measurements under constant and variable light conditions. Model performance was evaluated by comparing the differences between the root mean square error (RMSE) and mean square error (MSE) of observed and predicted values. The model exhibited predictive success for Fq'/Fm' and ETR under different temperature and light conditions with lower RMSE and MSE. However, prediction of F' and Fm' was poor due to a weak relationship under constant (R² = 0.48) and variable (R² = 0.35) light.     

基于多源遥感数据的草地净初级生产力质量评价

植被净初级生产力NPP(Net Primary Production)的遥感估算与分析对全球生态系统具有重要指导意义,不同尺度的遥感影像上占主导地位的地物景观信息是不同的,现代生态研究多尺度分析至关重要。以青海省海北藏族自治州为研究区,使用Landsat 8 OLI遥感影像、天宫二号宽波段成像仪影像、融合影像(Landsat8 OLI影像和天宫二号宽波段成像仪影像融合)联同MODIS影像,作为CASA模型的输入参数,探究不同尺度下的研究区域NPP的空间分布情况,并对比分析不同数据源数据在估算NPP时的精度。结果表明:(1)Landsat 8 OLI数据的NPP值位于150—200 g C m^-2 a^-1所占比例最高;天宫二号宽波段成像仪影像数据和融合后影像的NPP值位于50—100 g C m^-2 a^-1所占比例最高;MODIS数据的NPP值位于小于50 g C m^-2 a^-1比例最高。(2)天宫二号宽波段成像仪影像数据的均方根误差(RMSE)、平均绝对误...     

Comparison of the estimation capabilities of response surface methodology and artificial neural network for the optimization of recombinant lipase production by E. coli BL21

Response surface methodology (RSM) and artificial neural network (ANN) were used to optimize the effect of four independent variables, viz. glucose, sodium chloride (NaCl), temperature and induction time, on lipase production by a recombinant Escherichia coli BL21. The optimization and prediction capabilities of RSM and ANN were then compared. RSM predicted the dependent variable with a good coefficient of correlation determination (R ²) and adjusted R ² values for the model. Although the R ² value showed a good fit, absolute average deviation (AAD) and root mean square error (RMSE) values did not support the accuracy of the model and this was due to the inferiority in predicting the values towards the edges of the design points. On the other hand, ANN-predicted values were closer to the observed values with better R ², adjusted R ², AAD and RMSE values and this was due to the capability of predicting the values throughout the selected range of the design points. Similar to RSM, ANN could also be used to rank the effect of variables. However, ANN could not predict the interactive effect between the variables as performed by RSM. The optimum levels for glucose, NaCl, temperature and induction time predicted by RSM are 32 g/L, 5 g/L, 32°C and 2.12 h, and those by ANN are 25 g/L, 3 g/L, 30°C and 2 h, respectively. The ANN-predicted optimal levels gave higher lipase activity (55.8 IU/mL) as compared to RSM-predicted levels (50.2 IU/mL) and the predicted lipase activity was also closer to the observed data at these levels, suggesting that ANN is a better optimization method than RSM for lipase production by the recombinant strain.     

Sentinel-2 Satellite Imagery Application to Monitor Soil Salinity and Calcium Carbonate Contents in Agricultural Fields

The estuary tides affect groundwater dynamics; these areas are susceptible to waterlogging and salinity issues. A study was conducted on two fields with a total area of 60 hectares under a center pivot irrigation system that works with solar energy and belong to a commercial farm located in Northern Sudan. To monitor soil salinity and calcium carbonate in the area and stop future degradation of soil resources, easy, non-intrusive, and practical procedures are required. The objective of this study was to use remote sensing-determined Sentinel-2 satellite imagery using various soil indices to develop prediction models for the estimation of soil electrical conductivity (EC) and soil calcium carbonate (CaCO₃). Geo-referenced soil samples were collected from 72 locations and analyzed in the laboratory for soil EC and CaCO₃. The electrical conductivity of the soil saturation paste extract was represented by average values in soil dataset samples from two fields collected from the topsoil layer (0 to 15 cm) characteristic of the local salinity gradient. The various soil indices, used in this study, were calculated from the Sentinel-2 satellite imagery. The prediction was determined using the root mean square error (RMSE) and cross validation was done using coefficient of determination. The results of regression analysis showed linear relationships with significant correlation between the EC analyzed in laboratory and the salinity index-2 “SI2” (Model-1: R² = 0.59, p = 0.00019 and root mean square error (RMSE = 1.32%) and the bare soil index “BSI” (Model-2: R² = 0.63, p = 0.00012 and RMSE = 6.42%). Model-1 demonstrated the best model for predicting soil EC, and validation R² and RMSE values of 0.48% and 1.32%, respectively. The regression analysis results for soil CaCO₃ determination showed linear relationships with data obtained in laboratory and the bare soil index “BSI” (Model- 3: R² = 0. 45, p = 0.00021 and RMSE = 1.29%) and the bare soil index “BSI” & Normalized difference salinity index “NDSI” (Model-4: R² = 0.53, p = 0.00015 and RMSE = 1.55%). The validation confirmed the Model-3 results for prediction of soil CaCO₃ with R² and RMSE values of 0.478% and 1.29%, respectively. Future soil monitoring programs might consider the use of remote sensing data for assessing soil salinity and CaCO₃ using soil indices results generated from satellite image (i.e., Sentinel-2).     

Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province,China

Background

Cases of hemorrhagic fever with renal syndrome (HFRS) are widely distributed in eastern Asia, especially in China, Russia, and Korea. It is proved to be a difficult task to eliminate HFRS completely because of the diverse animal reservoirs and effects of global warming. Reliable forecasting is useful for the prevention and control of HFRS.

Methods

Two hybrid models, one composed of nonlinear autoregressive neural network (NARNN) and autoregressive integrated moving average (ARIMA) the other composed of generalized regression neural network (GRNN) and ARIMA were constructed to predict the incidence of HFRS in the future one year. Performances of the two hybrid models were compared with ARIMA model.

Results

The ARIMA, ARIMA-NARNN ARIMA-GRNN model fitted and predicted the seasonal fluctuation well. Among the three models, the mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of ARIMA-NARNN hybrid model was the lowest both in modeling stage and forecasting stage. As for the ARIMA-GRNN hybrid model, the MSE, MAE and MAPE of modeling performance and the MSE and MAE of forecasting performance were less than the ARIMA model, but the MAPE of forecasting performance did not improve.

Conclusion

Developing and applying the ARIMA-NARNN hybrid model is an effective method to make us better understand the epidemic characteristics of HFRS and could be helpful to the prevention and control of HFRS.     

A Comparative Assessment of the Influences of Human Impacts on Soil Cd Concentrations Based on Stepwise Linear Regression,Classification and Regression Tree,and Random Forest Models

Soil cadmium (Cd) contamination has attracted a great deal of attention because of its detrimental effects on animals and humans. This study aimed to develop and compare the performances of stepwise linear regression (SLR), classification and regression tree (CART) and random forest (RF) models in the prediction and mapping of the spatial distribution of soil Cd and to identify likely sources of Cd accumulation in Fuyang County, eastern China. Soil Cd data from 276 topsoil (0–20 cm) samples were collected and randomly divided into calibration (222 samples) and validation datasets (54 samples). Auxiliary data, including detailed land use information, soil organic matter, soil pH, and topographic data, were incorporated into the models to simulate the soil Cd concentrations and further identify the main factors influencing soil Cd variation. The predictive models for soil Cd concentration exhibited acceptable overall accuracies (72.22% for SLR, 70.37% for CART, and 75.93% for RF). The SLR model exhibited the largest predicted deviation, with a mean error (ME) of 0.074 mg/kg, a mean absolute error (MAE) of 0.160 mg/kg, and a root mean squared error (RMSE) of 0.274 mg/kg, and the RF model produced the results closest to the observed values, with an ME of 0.002 mg/kg, an MAE of 0.132 mg/kg, and an RMSE of 0.198 mg/kg. The RF model also exhibited the greatest R² value (0.772). The CART model predictions closely followed, with ME, MAE, RMSE, and R² values of 0.013 mg/kg, 0.154 mg/kg, 0.230 mg/kg and 0.644, respectively. The three prediction maps generally exhibited similar and realistic spatial patterns of soil Cd contamination. The heavily Cd-affected areas were primarily located in the alluvial valley plain of the Fuchun River and its tributaries because of the dramatic industrialization and urbanization processes that have occurred there. The most important variable for explaining high levels of soil Cd accumulation was the presence of metal smelting industries. The good performance of the RF model was attributable to its ability to handle the non-linear and hierarchical relationships between soil Cd and environmental variables. These results confirm that the RF approach is promising for the prediction and spatial distribution mapping of soil Cd at the regional scale.     

华南地区亚热带树木叶面积指数的高光谱反演研究

为构建树种叶面积指数的估算模型,以NDVI、RVI、FREP、CIGreen、CIRed-edge、MSAVI2为高光谱特征变量,通过统计分析,确定反演树种叶面积指数的最佳光谱特征变量,构建华南农业大学校园内50种亚热带树木的叶片反射率和叶面积指数(LAI)模型。结果表明,6种高光谱特征变量与树种叶面积指数间都具有极显著相关性,其中红边位置反射率(FREP)和比值植被指数(RVI)与LAI的拟合方程的R2都大于0.8,决定系数分别为0.820和0.811。经过精度验证,FREP估算的均方根误差(RMSE)只有0.13,该回归模型为估测亚热带典型树种的叶片LAI最佳模型。从高光谱遥感的角度结合亚热带植被的群落结构特点来看,建立的红边位置光谱反射率与叶面积指数的回归模型普遍具有较高的拟合度,所以利用高光谱特征变量反演亚热带树木叶片的叶面积指数等植被参数的应用前景较好。     

基于带宽优选地理加权回归模型的深圳市植被碳储量反演

植被碳储量估测是自然资源监测的重要内容,遥感技术结合地面样地进行反演可以获得区域范围内植被碳储量的空间连续分布,弥补了传统人工抽样调查估测的不足。然而,现有的参数和非参数遥感估测模型大多忽略了样地数据的变异与空间自相关关系。研究以Landsat 8 OLI影像为数据源提取遥感变量,结合植被碳储量实测调查数据,利用最小信息准则(AICc)、最大空间自相关距离(MSAD)和交叉验证(CV)分别确定最优带宽,组合Gaussian、Bi-square和Exponential核函数构建地理加权回归(GWR)模型估算深圳市植被碳储量,并与多元线性回归(MLR)进行比较,选择最优模型绘制深圳市植被碳储量空间分布图。研究结果表明,GWR模型整体精度优于MLR模型,GWR模型的决定系数(R~2)均高于MLR模型,且均方根误差(RMSE)和平均绝对误差(MAE)显著降低。带宽和核函数的选择对GWR模型估测结果产生了显著影响。以CV确定带宽、Exponential为核函数组合构建的GWR模型效果最佳,其R~2为0.697,RMSE为10.437 Mg C/hm~2,相比其它模型精度上升了13.87%—32....     

Application of linear models for estimation of leaf area in soybean [<Emphasis Type="Italic">Glycine max</Emphasis> (L.) Merr]

Leaf area estimation is an important measurement for comparing plant growth in field and pot experiments. In this study, determination of the leaf area (LA, cm²) in soybean [Glycine max (L.) Merr] involves measurements of leaf parameters such as maximum terminal leaflet length (L, cm), width (W, cm), product of length and width (LW), green leaf dry matter (GLDM) and the total number of green leaflets per plant (TNLP) as independent variables. A two-year study was carried out during 2009 (three cultivars) and 2010 (four cultivars) under field conditions to build a model for estimation of LA across soybean cultivars. Regression analysis of LA vs. L and W revealed several functions that could be used to estimate the area of individual leaflet (LE), trifoliate (T) and total leaf area (TLA). Results showed that the LW-based models were better (highest R ² and smallest RMSE) than models based on L or W and models that used GLDM and TNLP as independent variables. The proposed linear models are: LE = 0.754 + 0.655 LW, (R ² = 0.98), T = −4.869 + 1.923 LW, (R ² = 0.97), and TLA = 6.876 + 1.813 ΣLW (summed product of L and W terminal leaflets per plant), (R ² = 0.99). The validation of the models based on LW and developed on cv. DPX showed that the correlation between calculated and measured LA was strong. Therefore, the proposed models can estimate accurately and massively the LA in soybeans without the use of expensive instrumentation.     

多源多角度遥感数据反演森林叶面积指数方法

利用北京1号和Landsat多源数据组合成4个角度多波段数据集, 在考虑森林三维垂直分布特点的基础上, 结合INFORM几何光学与辐射传输混合模型, 通过聚类+神经元网络方式, 建立相应的多源多角度LAI反演模型。最后利用实地LAI测量数据和MODIS LAI产品, 对不同角度组合和噪声水平下的LAI反演结果进行验证。结果表明: 在保证数据质量的条件下, 通过增加角度可以提高森林的LAI反演精度, 最终R²=0.713, RMSE=0.957, 比单个角度的反演精度平均提高约20%。     

Leaf area expansion and assimilate production in sunflower (Helianthus annuus L.) growing under low phosphorus conditions

Reductions in leaf area and plant growth as a consequence of phosphorus (P) limitations have been attributed both to direct effects of P shortage on leaf expansion rate and to a reduced production of assimilates required for growth. Canopy assimilation and leaf area expansion are closely interrelated processes. In this work we used experimental and simulation techniques to identify and study their importance in determining leaf area on sunflower (Helianthus annuus L.) growing under P-deficient conditions. Experiment 1 was done outdoors, in Buenos Aires, Argentina, and Experiment 2 in a glasshouse in Wageningen, The Netherlands. In both experiments we studied the effects of soil P addition on leaf appearance, leaf expansion, dry matter accumulation, and leaf photosynthesis of non-water stressed plants grown in pots containing a P-deficient soil. Before sowing the equivalent amounts of 0–600 kg of super phosphate ha^-1 were added to the pots. Phosphorus deficiency delayed leaf appearance increasing the value of the phyllochron (PHY) up to 76%, the rate of leaf area expansion during the quasi-linear phase of leaf expansion (LER) was reduced by up to 74%, with respect to high P plants. Phosphorus deficiency reduced by up to 50% the rate of light saturated photosynthesis per unit of leaf area (AMAX) in recently expanded leaves, while at low levels of leaf insertion in the canopy, AMAX was reduced by up to 85%, when compared to that in high P plants. Phosphorus deficiency also reduced the duration of the quasi-linear phase of leaf expansion by up to eight days. The values of LER were related (r = 0.56, P < 0.05) to the mean concentration of P in all the leaves (Leaves P%) and not to the concentration of P in the individual leaf where LER was determined (r = 0.22, P < 0.4) suggesting that under P deficiency individual leaf expansion was not likely to be regulated by the total P concentration at leaf level. The values of AMAX of individual leaves were related (r = 0.79, P < 0.01) to the concentration of total P in the corresponding leaf (Leaf P%). LER showed a hyperbolic relationship with Leaves P% (R² = 0.94, P < 0.01, n = 13) that saturate at 0.14%. AMAX showed a hyperbolic relationship with Leaf P% (R² = 0.73, P < 0.01, n = 53) that saturated with values of Leaf P% higher than 0.22. A morphogenetic model of leaf area development and growth was developed to quantify the effect of assimilate supply at canopy level on total leaf area expansion, and to study the effects of model parameters on the growth of sunflower plants under P-deficient conditions. With this model we identified the existence of direct effects of P deficiency on individual leaf area expansion. However, we calculated that under mild P stress conditions up to 83% of the reduction in the observed leaf area was explained by the particular effects of P% on the rate of leaf appearance, on the duration of the linear period of leaf expansion, and on the value of AMAX. We also calculated that the effects of P deficiency on the value of AMAX alone, explained up to 41% of the observed reductions in total leaf area between the highest and the intermediate P level in Experiment 2. Possible mechanisms of action of the direct effects of P on individual leaf expansion are discussed in this paper.     

人工长白落叶松立木叶面积预估模型

叶面积影响着树木干物质的生产,进而影响树木乃至整个林分的生长,而叶面积准确估计对分析树木和林分生长具有重要作用.本研究基于黑龙江省长白落叶松人工林中76株解析木数据,分别建立枝条层面和单木层面的叶面积预估模型.结果表明: 考虑样木层次随机效应的最优枝条叶面积混合效应模型包含lnBD(BD为枝条基径)、lnRDINC(RDINC为相对着枝深度)和lnCR(CR为冠长率)3个随机效应参数,具体形式为:lnBLA=β₁+(β₂+b₂)lnBD+(β₃+b₃)lnRDINC+β₄lnDBH+β₅lnHT/DBH+(β₆+b₆)lnCR,其中:β_i和b_i分别是模型的固定效应参数和随机效应参数;DBH为树木胸高处直径;HT/DBH为树高与胸径的比值.模型的修正决定系数(R_a²)为0.90,均方根误差(RMSE)为0.5477,平均偏差(ME)为-0.03,平均绝对偏差(MAE)为0.24,预测精度(P)为91%,枝条叶面积预估模型的预估效果较好.以枝条叶面积预估模型为基础,计算树冠叶面积并建立树冠叶面积预估模型,最终形式为:lnCLA=γ₀+γ₁lnDBH+γ₂CR,其中,γ_i为模型参数.似然比检验结果(P>0.05)说明该模型不用考虑样地层次的随机效应.本研究所建立的立木树冠叶面积预估模型的决定系数(R²)为0.87,RMSE为0.3847,拟合效果好,可以很好地预测人工长白落叶松立木树冠叶面积,为以后叶面积分布和光合作用的研究提供了理论基础.     

Estimating biophysical parameters of rice with remote sensing data using support vector machines

Hyperspectral reflectance (350–2500 nm) measurements were made over two experimental rice fields containing two cultivars treated with three levels of nitrogen application. Four different transformations of the reflectance data were analyzed for their capability to predict rice biophysical parameters, comprising leaf area index (LAI; m² green leaf area m⁻² soil) and green leaf chlorophyll density (GLCD; mg chlorophyll m⁻² soil), using stepwise multiple regression (SMR) models and support vector machines (SVMs). Four transformations of the rice canopy data were made, comprising reflectances (R), first-order derivative reflectances (D1), second-order derivative reflectances (D2), and logarithm transformation of reflectances (LOG). The polynomial kernel (POLY) of the SVM using R was the best model to predict rice LAI, with a root mean square error (RMSE) of 1.0496 LAI units. The analysis of variance kernel of SVM using LOG was the best model to predict rice GLCD, with an RMSE of 523.0741 mg m⁻². The SVM approach was not only superior to SMR models for predicting the rice biophysical parameters, but also provided a useful exploratory and predictive tool for analyzing different transformations of reflectance data.     

深圳市前海桂湾公园土壤蒸发及植被蒸腾模拟

蒸散发（ET）是连接水文循环和地表能量平衡的重要组成部分,准确的估算土壤蒸发（LE_s）和植被蒸腾（LE_v）对城市水资源分配和管理具有重要意义。针对城市林地蒸散发双源模型的缺失,本研究基于MOD16模型提出了应用于城市林地区域改进的MOD16双源模型。改进的MOD16双源模型更加准确的描述城市林地区域复杂下垫面的能量分配过程。结合高时空分辨率的Sentinel-2遥感卫星影像,对2020年深圳市前海桂湾公园20个无云日的LE_s和LE_v进行反演研究。用Shuttleworth-Wallace （S-W）模型和双作物系数法（FAO dual-K_c）验证模型性能,同时分析改进的MOD16模型对输入变量的敏感度,结果表明：改进的MOD16模型与S-W模型和FAO dual-K_c之间的均方根误差（RMSE）分别为21.39 W/m²和20.41 W/m²,平均绝对误差（MAE）分别为18.81 W/m²和19.05 W/m²,R²分别为0.801和0.634。改进的MOD16模型可以应用在城市林地LE_s和LE_v估算中。桂湾公园地区总蒸散月均值在85-165 W/m²之间。研究区域的LE_s和LE_v呈现出明显的季节变化,春夏季蒸散量升高,秋冬季蒸散量降低,LE_s的变化范围为0-50 W/m²,LE_v的变化范围为0-120 W/m²。LE_v高值在研究区呈现零散分布,多集中在前海桂湾沿岸,LE_s高值集中在研究区的西北、东北和东南部。敏感性分析结果表明,改进后的MOD16模型对植被覆盖、太阳辐射和湿度更敏感。其中,LE_v模拟结果受净辐射和植被覆盖影响最大,LE_s的模拟结果受湿度和植被覆盖的影响最大。因此,应用改进的MOD16模型时需要优先确保这些参数的准确输入。修正后的MOD16模型极大地提高了高分辨率、小尺度区域城市林地LE_s和LE_v模拟的准确性,为准确获取植被耗水量信息从而科学指导城市林地灌溉、解决城市水资源分配与管理提供有力工具。     

Application of Artificial Neural Network for predicting biomass growth during domestic wastewater treatment through a biological process

The biological treatment process is responsible for removing organic and inorganic matter in wastewater. This process relies heavily on microorganisms to successfully remove organic and inorganic matter. The aim of the study was to model biomass growth in the biological treatment process. Multilayer perceptron (MLP) Artificial Neural Network (ANN) algorithm was used to model biomass growth. Three metrics: coefficient of determination (R²), root mean squared error (RMSE), and mean squared error (MSE) were used to evaluate the performance of the model. Sensitivity analysis was applied to confirm variables that have a strong influence on biomass growth. The results of the study showed that MLP ANN algorithm was able to model biomass growth successfully. R² values were 0.844, 0.853, and 0.823 during training, validation, and testing phases, respectively. RMSE values were 0.7476, 1.1641, and 0.7798 during training, validation, and testing phases respectively. MSE values were 0.5589, 1.3551, and 0.6081 during training, validation, and testing phases, respectively. Sensitivity analysis results showed that temperature (47.2%) and dissolved oxygen (DO) concentration (40.2%) were the biggest drivers of biomass growth. Aeration period (4.3%), chemical oxygen demand (COD) concentration (3.2%), and oxygen uptake rate (OUR) (5.1%) contributed minimally. The biomass growth model can be applied at different wastewater treatment plants by different plant managers/operators in order to achieve optimum biomass growth. The optimum biomass growth will improve the removal of organic and inorganic matter in the biological treatment process.