Suspended sediment load prediction of river systems: An artificial neural network approach

Information on suspended sediment load is crucial to water management and environmental protection. Suspended sediment loads for three major rivers (Mississippi, Missouri and Rio Grande) in USA are estimated using artificial neural network (ANN) modeling approach. A multilayer perceptron (MLP) ANN with an error back propagation algorithm, using historical daily and weekly hydroclimatological data (precipitation P_(t), current discharge Q_(t), antecedent discharge Q_(t−1), and antecedent sediment load SL_(t−1)), is used to predict the suspended sediment load SL_(t) at the selected monitoring stations. Performance of ANN was evaluated using different combinations of input data sets, length of record for training, and temporal resolution (daily and weekly data). Results from ANN model were compared with results from multiple linear regressions (MLR), multiple non-linear regression (MNLR) and Autoregressive integrated moving average (ARIMA) using correlation coefficient (R), mean absolute percent error (MAPE) and model efficiency (E). Comparison of training period length was also made (4, 3 and 2 years of training and 1, 2 and 3 years of testing, respectively). The model efficiency (E) and R² values were slightly higher for the 4 years of training and 1 year of testing (4 * 1) for Mississippi River, indifferent for Missouri and slightly lower for Rio Grande River. Daily simulations using Input 1 (P_(t), Q_(t), Q_(t−1), SL_(t−1)) and three years of training and two years of testing (3 * 2) performed better (R² and E of 0.85 and 0.72, respectively) than the simulation with two years of training and three years of testing (2 * 3) (R² and E of 0.64 and 0.46, respectively). ANN predicted daily values using Input 1 and 3 * 2 architecture for Missouri (R² = 0.97) and Mississippi (R² = 0.96) were better than those of Rio Grande (R² = 0.65). Daily predictions were better compared to weekly predictions for all three rivers due to higher correlation within daily than weekly data. ANN predictions for most simulations were superior compared to predictions using MLR, MNLR and ARIMA. The modeling approach presented in this paper can be potentially used to reduce the frequency of costly operations for sediment measurement where hydrological data is readily available.     

Inhibition of in vitro lymphocyte blastogenesis by chicken alpha-fetoprotein

Chicken alpha-fetoprotein (ch-AFP), purified from fetal chicken serum and embryo extracts, respectively, was examined for its immunomodulatory effect in vitro. Significant (P less than 0.05) suppression of the allogeneic mixed lymphocyte reaction (MLR) was observed, when these preparations were added to one-way mixed lymphocyte cultures (MLC) in quantities of 62.5-1000 micrograms/ml. Suppression of the MLR was depending on the presence of ch-AFP for at least 16 h after initiation of the MLC, suggesting that this fetal protein was acting mainly in the early phase of lymphoblastogenesis. Serum of chicken embryos (12th and 15th day of incubation), day-old chickens, and of 10-week-old chickens of four different inbred lines were also found to exert suppression of the MLR. From these data, it is hypothesized that ch-AFP plays an immunoregulatory role by maintaining a certain stage of self tolerance during differentiation of the avian immune system.     

Artificial neural network approach for prediction of ammonia emission from field-applied manure and relative significance assessment of ammonia emission factors

This article presents a systematic method for enhancing the estimation accuracy of ammonia emission from field-applied manure and for assessing the relative significance of ammonia emission factors, using the feedforward-backpropagation artificial neural network (ANN) approach.

The multivariate linear regression (MLR) method well describes the ammonia emission tendency with the emission factor variation. However, ammonia emission from manure slurry is too complex to be captured in a linear regression model. This necessitates a model which can describe complex nonlinear effects between the ammonia emission variables such as soil and manure states, climate and agronomic factors. In the present study, a principle component analysis (PCA) based preprocessing and weight partitioning method (WPM) based postprocessing ANN approach (called the PWA approach) is proposed to account for the complex nonlinear effects.

The ammonia emission is predicted with precision by the 11 emission factors, using the nonlinear ANN approach. The relative importance among the 11 emission factors is identified using the elasticity analysis in the MLR method and using the WPM in the ANN approach. The relative significance obtained quantitatively by the PWA approach in the present study gives an excellent explanation of the most important processes controlling NH₃ emission.     

Urban Green infrastructures: How much did they affect property prices in Singapore?

In 2015, 17 Sustainable Development Goals were outlined within the 2030 Agenda by the United Nations. Objective 11.7 aims to provide universal access to safe, inclusive, and accessible green and public spaces, highlighting the strategic role of these areas in cities. In the international literature, the theory of Ecosystem Services (ESs) has been developed to raise public awareness of the need to preserve biodiversity, enhance community cohesion, civic identity, and quality of life. In this study, we explored the economic value of Singapore's Urban Green Infrastructures (UGI) by investigating the private condominium and apartment unit market through the Hedonic Pricing Method (HPM). The HPM was integrated with Geographic Information System (GIS) to spatialize housing units, measure the distance of different green spaces, and consider the dependence effects among housing unit transactions. The results highlighted a positive effect on values of the proximity to the natural green areas, as well as to the regional, city parks, and small nature areas. The annual benefits of UGIs on households within 800 m range from 10,305,275 USD for nature areas to 59,723,703 USD for the city parks and 74,011,689 USD for the regional parks. Estimates showed the small contribution of park connectors (PCN) and neighborhood parks. The HPM results are a useful aid to understanding the amenity value of UGIs. The modeling outcomes could be used to inform policymakers and municipal green managers about UGIs preservation and new allocation starting from households’ preferences.     

Spatial modeling of the carbon stock of forest trees in Heilongjiang Province,China

Heilongjiang province is the largest forest zone in China and the forest coverage rate is 46%. Forests of Heilongjiang province play an important role in the forest ecosystem of China. In this study we investi- gated the spatial distribution of forest carbon storage in Heilongjiang province using 3083 plots sampled in 2010. We attempted to fit two global models, ordinary least squares model （OLS）, linear mixed model （LMM）, and a local model, geographically weighted regression model （GWR）, to the relationship between forest carbon content and stand, environment, and climate factors. Five predictors significantly affected forest carbon storage and spatial distribution, viz. average diameter of stand （DBH）, number of trees per hectare （TPH）, elevation （Elev）, slope （Slope） and the product of precipitation and temperature （Rain Temp）. The GWR model outperformed the two global models in both model fitting and prediction because it successfully reduced both spatial auto- correlation and heterogeneity in model residuals. More importantly, the GWR model provided localized model coefficients for each location in the study area, which allowed us to evaluate the influences of local stand conditions and topographic features on tree and stand growth, and forest carbon stock. It also helped us to better understand the impacts of silvi- cultural and management activities on the amount and changes of forest carbon storage across the province. The detailed information can be readily incorporated with the mapping ability of GIS software to provide excellent tools for assessing the distribution and dynamics of the for- est-carbon stock in the next few years.     

Multivariate analysis of nitrogen content for rice at the heading stage using reflectance of airborne hyperspectral remote sensing

Airborne hyperspectral remote sensing was adapted to establish a general-purpose model for quantifying nitrogen content of rice plants at the heading stage using three years of data. There was a difference in dry mass and nitrogen concentration due to the difference in the accumulated daily radiation (ADR) and effective cumulative temperature (ECT). Because of these environmental differences, there was also a significant difference in nitrogen content among the three years. In the multiple linear regression (MLR) analysis, the accuracy (coefficient of determination: R², root mean square of error: RMSE and relative error: RE) of two-year models was better than that of single-year models as shown by R² ≥ 0.693, RMSE ≤ 1.405 g m⁻² and RE ≤ 9.136%. The accuracy of the three-year model was R² = 0.893, RMSE = 1.092 g m⁻² and RE = 8.550% with eight variables. When each model was verified using the other data, the range of RE for two-year models was similar or increased compared with that for single-year models. In the partial least square regression (PLSR) model for the validation, the accuracy of two-year models was also better than that of single-year models as R² ≥ 0.699, RMSE ≤ 1.611 g m⁻² and RE ≤ 13.36%. The accuracy of the three-year model was R² = 0.837, RMSE = 1.401 g m⁻² and RE = 11.23% with four latent variables. When each model was verified, the range of RE for two-year models was similar or decreased compared with that for single-year models. The similarities and differences of loading weights for each latent variable depending on hyperspectral reflectance might have affected the regression coefficients and the accuracy of each prediction model. The accuracy of the single-year MLR models was better than that of the single-year PLSR models. However, accuracy of the multi-year PLSR models was better than that of the multi-year MLR models. Therefore, PLSR model might be more suitable than MLR model to predict the nitrogen contents at the heading stage using the hyperspectral reflectance because PLSR models have more sensitive than MLR models for the inhomogeneous results. Although there were differences in the environmental variables (ADR and ECT), it is possible to establish a general-purpose prediction model for nitrogen content at the heading stage using airborne hyperspectral remote sensing.     

基于光谱分析的温室番茄叶片叶绿素含量预测

通过分析叶片光谱反射率与其叶绿素含量的相关关系表明,温室番茄叶片的光谱反射率与其叶绿素含量的敏感波段为510～625 nm和690～710 nm,最佳波长为526 nm、609 nm和697 nm.利用最佳波长处的光谱反射率与多种建模方法如多元回归分析MLR(Multilinear Regression)、偏最小二乘回归分析PLSR(Partial Least Square Regression)建立了预测叶片叶绿素含量的模型,建模相关系数很相近,均大于0.740,但是PLSR在一定程度上消除了多重相关性的影响,模型验证时的相关系数(0.768)大于MLR模型(0.740);本研究在NDVI的基础上提出了一个新的光谱指数NDCI,并基于NDCI建立了叶片叶绿素含量的预测模型(Rc=0.753),获得了比较好的预测效果(Rv=0.761),为作物长势检测仪的开发奠定了基础.     

牛肉嫩度的高光谱法检测技术

为实现对牛肉嫩度的预测和分级,构建了试验用高光谱检测系统,在400～1000nm波长范围内获取牛肉表面的高光谱散射图像.从高光谱图像中提取牛肉的反射光谱曲线,用step-wise逐步回归法选择 430、496、510、725、760和828nm 6个波长建立了多元线性回归模型,用全交叉验证法验证模型的预测效果,模型的预测相关系数为0.96,预测标准差为0.64kg.以嫩度6.0kg为界将样本分为嫩牛肉和粗糙牛肉2类,特征波长处反射值为变量,建立了正则判别函数对牛肉嫩度分级,用全交叉验证法验证训练的效果.嫩牛肉分级准确率为83.3%,较粗糙牛肉分级准确率为90.9%,总的分级准确率为87.0%.研究表明该预测和分级技术具有一定的可行性.     

土壤水分的高光谱响应特性及定量监测研究

为及时、准确地监测土壤含水量（SMC），采用室内条件下人工模拟不同SMC环境的方法，通过测定各时间段的SMC及其对应的土壤光谱反射率，运用连续投影算法（SPA）提取土壤水分的特征波长，结合多元线性回归（MLR）方法，构建SMC的高光谱定量监测模型。结果表明，光谱反射率随着样本SMC的增加而逐渐降低，二者存在明显的负相关关系；采用SPA方法提取的光谱特征波段为422、629、817、976、1121、1258、1359、1448、1830和2022nm；构建的SPA-MLR土壤水分高光谱监测模型表现出良好的预测效果（校正集的R2=0.930、RMSE=8.845、RPD=3.794，验证集的R2=0.927、RMSE=8.799、RPD=3.581）。研究结果可为土壤水分的高效精准监测提供一定的实践探索和理论参考。     

成渝城市群景观生态风险与人类活动强度时空关联分析

成渝城市群承担着重要的经济发展与生态安全责任，探讨快速发展背景下景观生态风险受人类活动强度的影响效应及变动趋势，对于地区规划发展及生态治理具有重要意义。基于2000、2010和2020年三期成渝城市群土地利用遥感数据，构建景观生态风险、人类活动强度评价方法，并基于GWR模型、双变量局部空间相关性分析、耦合测度，揭示两者的时空关联特征。结果显示：（1）2000—2020年研究区ERI逐渐改善，风险呈中间高、四周低的特征，且中心城市在2020年降为低风险。（2）研究区HAI显著提高，空间分布与ERI较为统一，主要以中心城市向外辐射扩张为趋势。（3）2000—2020年间负相关系数由中心城市扩张至整个城市群中部，ERI与HAI间空间正相关性不断减弱，高-高聚集区主要集中于研究区中部城市，低-低聚集区分布在山地林区，低-高及高-低聚集区均有增加趋势；两个指标耦合协调度在20年间显著提升，研究区中部高度协调面积扩张明显。妥善治理生态风险、科学规划发展策略可将人地矛盾转为相互促进的新局面，研究结论可为地区生态风险治理、合理谋划发展提供科学参考。