A Novel Hybrid Ensemble Learning Approach for Enhancing Accuracy and Sustainability in Wind Power Forecasting

Accurate wind power forecasting is critical for system integration and stability as renewable energy reliance grows.Traditional approaches frequently struggle with complex data and non-linear connections. This article presentsa novel approach for hybrid ensemble learning that is based on rigorous requirements engineering concepts.The approach finds significant parameters influencing forecasting accuracy by evaluating real-time Modern-EraRetrospective Analysis for Research and Applications (MERRA2) data from several European Wind farms usingin-depth stakeholder research and requirements elicitation. Ensemble learning is used to develop a robust model,while a temporal convolutional network handles time-series complexities and data gaps. The ensemble-temporalneural network is enhanced by providing different input parameters including training layers, hidden and dropoutlayers along with activation and loss functions. The proposed framework is further analyzed by comparing stateof-the-art forecasting models in terms of Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE),respectively. The energy efficiency performance indicators showed that the proposed model demonstrates errorreduction percentages of approximately 16.67%, 28.57%, and 81.92% for MAE, and 38.46%, 17.65%, and 90.78%for RMSE for MERRAWind farms 1, 2, and 3, respectively, compared to other existingmethods. These quantitativeresults show the effectiveness of our proposed model with MAE values ranging from 0.0010 to 0.0156 and RMSEvalues ranging from 0.0014 to 0.0174. This work highlights the effectiveness of requirements engineering in windpower forecasting, leading to enhanced forecast accuracy and grid stability, ultimately paving the way for moresustainable energy solutions.

Considering the Influence of Multi-weather-factors to Forecasting the Water Requirement of Well Irrigation Rice Based on ANN Model

The author considered the influences of several weather factors, such as air temperature, sunlight, saturation deficiency, wind speed and so on to forecasting the water requirement of well irrigation rice based on Artificial Neutron Network. Through dealing with the time series of water requirement and its influence factors, the author applied the multi-dimension data correlation analysis to ensure the net structure. Thus, the ANN model to forecast the water requirement of well irrigation rice has been built. By means of the ANN model, uncertainty relation between water requirement and many influence factors among the interior and exterior can be discovered. The results of ANN model is good, and can provide some references for establishing the water saving irrigation system.

Research on Forecasting Water Requirement of Well Irrigation Rice by Time Series Analysis Method

The paper builds up the forecasting model of air temperature according to the data (1994～1998) of Fu Jin area.At the same time,the writer inquires into the relation of water requirement of well irrigation rice (ET) and average air temperature (T).Furthermore,the rice irrigation water requirement (ET) of Fu Jin area has been forecast in 1999.Thus,we can apply the model in irrigation management.

Real-Time Modelling and Optimisation for Water and Energy Efficient Surface Irrigation

The viability and sustainability of crop production is currently threatened by increasing water scarcity. Water scarcity problems can be addressed through improved water productivity and the options usually presumed in this context are efficient water use and conversion of surface irrigation to pressurised systems. By replacing furrow irrigation with drip or centre pivot systems, the water efficiency can be improved by up to 30% to 45%. However, the installation and application of pumps and pipes, and the associated fuels needed for these alternatives increase energy consumption. A balance between the improvement in water use and the potential increase in energy consumption is required. When surface water is used, pressurised irrigation systems increase energy consumption substantially, by between 65% to 75%, and produce greenhouse gas emissions around 1.75 times higher than that of gravity based irrigation systems so their use should be carefully planned keeping in view adverse impact of carbon emissions on the environment and threat of increasing energy prices. With gravity-fed surface irrigation methods, the energy consumption is assumed to be negligible. This study has shown that a novel real-time infiltration model REIP has enabled implementation of real-time optimisation and gravity fed surface irrigation with real-time optimisation has potential to bring significant improvements in irrigation performance along with substantial water savings of 2.92 ML/ha which is equivalent to that given by pressurised systems. The real-time optimisation and control thus offers a modern, environment friendly and water efficient system with close to zero increase in energy consumption and minimal greenhouse gas emissions.

A STUDY ON THE ENSEMBLE FORECAST REAL-TIME CORRECTION METHOD

Using real-time correction technology for typhoons, this paper discusses real-time correction for forecasting the track of four typhoons during 2009 and 2010 in Japan, Beijing, Guangzhou, and Shanghai. It was determined that the short-time forecast effect was better than the original objective mode. By selecting four types of integration schemes after multiple mode path integration for those four objective modes, the forecast effect of the multi-mode path integration is better, on average, than any single model. Moreover, multi-mode ensemble forecasting has obvious advantages during the initial 36 h.

Assessing Suitability of Irrigation Scheduling Decision Support Systems for Lowland Rice Farmers in Sub-Saharan Africa—A Review

Irrigation in lowland rice production systems in Sub-Saharan Africa (SSA) is mainly based on traditional surface irrigation methods with continuous flooding practices. This irrigation method ends up using a lot more water that would have otherwise been used to open more land and be used in other water-requiring sectors. Various studies suggest Alternate Wetting and Drying (AWD) as an alternative practice for water management that reduces water use without significantly affecting yield. However, this practice has not been well adopted by the farmers despite its significant benefits of reduced total water use. Improving the adoption of AWD using irrigation Decision Support Systems (DSSs) helps the farmer on two fronts;to know “how much water to apply” and “when to irrigate”, which is very critical in maximizing productivity. This paper reviews the applicability of DSSs using AWD in lowland rice production systems in Sub-Saharan Africa.

An Assessment of Potential Economic Gain from Weather Forecast Based Irrigation Scheduling for Marginal Farmers in Karnataka, Southern State in India

This study is aimed to assess the usefulness of weather forecasts for irrigation scheduling in crops to economize water use. The short-term gains for the farmers come from reducing costs of irrigation with the help of advisory for when not to irrigate because rain is predicted (risk-free because the wrong forecast only delays irrigation within tolerance). Here, a quantitative assessment of saving (indirect income) if irrigation is avoided as rain is imminent (as per forecast), using a five-year archived forecast data over Karnataka state at hobli (a cluster of small villages) level is presented. Estimates showed that the economic benefits to the farmers from such advisories were significant. The potential gain in annual income from such forecast-based irrigation scheduling was of the order of 10% - 15%. Our analysis also indicated that the use of advisory by a small percentage of more than 10 million marginal farmers (landholding < 3 acres) in Karnataka could lead to huge cumulative savings of the order of many crores.

A Real-Time Fraud Detection Algorithm Based on Usage Amount Forecast

Real-time Fraud Detection has always been a challenging task, especially in financial, insurance, and telecom industries. There are mainly three methods, which are rule set, outlier detection and classification to solve the problem. But those methods have some drawbacks respectively. To overcome these limitations, we propose a new algorithm UAF (Usage Amount Forecast).Firstly, Manhattan distance is used to measure the similarity between fraudulent instances and normal ones. Secondly, UAF gives real-time score which detects the fraud early and reduces as much economic loss as possible. Experiments on various real-world datasets demonstrate the high potential of UAF for processing real-time data and predicting fraudulent users.

Real-Time Monitoring and Forecast of Active Population Density Using Mobile Phone Data

Real-time monitoring and forecast of large scale active population density is of great significance as it can warn and prevent possible public safety accident caused by abnormal population aggregation.Active population is defined as the number of people with their mobile phone powered on.Recently,an unfortunate deadly stampede occurred in Shanghai on December 31th 2014 causing the death of 39 people.We hope that our research can help avoid similar unfortunate accident from happening.In this paper we propose a method for active population density real-time monitoring and forecasting based on data from mobile network operators.Our method is based solely on mobile network operators existing infrastructure and barely requires extra investment,and mobile devices play a very limited role in the process of population locating.Four series forecasting methods,namely Simple Exponential Smoothing(SES),Double exponential smoothing(DES),Triple exponential smoothing(TES)and Autoregressive integrated moving average(ARIMA)are used in our experiments.Our experimental results suggest that we can achieve good forecast result for 135 min in future.

Construction Simulation and Real-Time Control for High Arch Dam

A method of combining dynamic simulation with real-time control was proposed to fit the randomness and uncertainty in the high arch dam construction process. The mathematical logic model of high arch dam construction process was established. By combining dynamic construction simulation with schedule analysis, the process of construction schedule forecasting and analysis based on dynamic simulation was studied. The process of real-time schedule control was constructed and some measures for dynamic adjustment and control of construction schedule were provided. A system developed with the method is utilized in a being constructed hydroelectric project located at the Yellow River in northwest China, which can make the pouring plan of the dam in the next stage (a month, quarter or year) to guide the practical construction. The application result shows that the system provides an effective technical support for the construction and management of the dam.

Rainfall-runoff simulation and flood forecasting for Huaihe Basin

The main purpose of this study was to forecast the inflow to Hongze Lake using the Xin＇anjiang rainfall-runoff model. The upper area of Hongze Lake in the Huaihe Basin was divided into 23 sub-basins, including the surface of Hongze Lake. The influence of reservoirs and gates on flood forecasting was considered in a practical and simple way. With a one-day time step, the linear and non-linear Muskingum method was used for channel flood routing, and the least-square regression model was used for real-time correction in flood forecasting. Representative historical data were collected for the model calibration. The hydrological model parameters for each sub-basin were calibrated individually, so the parameters of the Xin＇anjiang model were different for different sub-basins. This flood forecasting system was used in the real-time simulation of the large flood in 2005 and the results are satisfactory when compared with measured data from the flood.

Development of a concentration method for detection of tobacco mosaic virus in irrigation water

Tobacco mosaic virus(TMV) causes significant yield loss in susceptible crops irrigated with contaminated water. However, detection of TMV in water is difficult owing to extremely low concentrations of the virus. Here, we developed a simple method for the detection and quantification of TMV in irrigation water. TMV was reliably detected at concentrations as low as 10 viral copies/μL with real-time PCR. The sensitivity of detection was further improved using polyethylene glycol 6000(PEG6000, MW 6000) to concentrate TMV from water samples. Among the 28 samples from Shaanxi Province examined with our method, 17 were tested positive after virus concentration. Infectivity of TMV in the original water sample as well as after concentration was confirmed using PCR. The limiting concentration of TMV in water to re-infect plants was determined as 102 viral copies/mL. The method developed in this study offers a novel approach to detect TMV in irrigation water, and may provide an effective tool to control crop infection.

Modeling the Effect of Irrigation Practices in Flash Floods: A Case Study for the US Southwest

Conventional streamflow forecasting does not generally take into account the effects of irrigation practice on the magnitude of floods and flash floods. In this paper, we report the results of a study in which we modeled the impacts of an irrigated area in the US Southwest on streamflow. A calibrated version of the Variable Infiltration Capacity model (VIC), coupled with a routing algorithm, was used to investigate two strategies for irrigating alfalfa in the Beaver Creek watershed (Arizona, USA), for the period January to March of 2010, at a resolution of 1.8 km and hourly time step. By incorporating the effects of irrigation in artificially maintaining soil moisture, model performance is improved without requiring changes in the resolution or quality of input data. Peak flows in the watershed were found to increase by 10 to 500 times, depending on the irrigation scenario, as a function of the strategy and the intensity of rainfall. The study suggests that both flood control and irrigation efficiency could be enhanced by applying improved irrigation techniques.

Key Developments in Indian Irrigation Sector

The key developments in Indian Irrigation sector have been presented by briefly discussing the following topics:1.Present Indian Irrigation Challenges and Way Forward.2.Regulatory Interventions in Water Sector in India(Maharashtra’s Example).3.Roles and Activities of Maharashtra Water Resource Regulatory Authority(MWRRA).4.Major Achievements of MWRRA.5.Indian National Committee On Irrigation and Drainage(INCID).6.Irrigation,Command Area Development and Micro Irrigation in India.7.Flood Management and Its Measures.8.Capacity Building.

智慧灌溉大数据管理平台设计与应用

以粗放型为主的漫灌方式浪费水资源,探索高效节水农业灌溉意义重大。本研究研制了集数据采集、数据管理、数据可视化、分析决策和远程管理为一体的智慧灌溉大数据管理平台,旨在以数字化管理与智能化控制方式提升水资源利用效率。平台利用嵌入式、物联网、互联网、3S(GIS、GPS、RS)等技术,采取“1+1+N”的设计模式,构建作物需水预报模型与灌溉决策模型,基于B/S构架和Java语言,设计了1个灌溉数据中心、1个灌溉数据管理系统、4个应用系统,打造了智慧灌溉大数据管理平台。平台在河北、河南、山东、江苏等地区设有多个示范基地,汇聚了8个科研小组、24个试验基地的有关多种作物的生长、灌溉、气象、土壤等数据,平均采集数据18829条/天,帮助管理人员摸清家底;集成了多个团队的软件系统和62套物联网设备,及时、定量地呈现了农作物生长状况及环境状态,实现了农作区动态监测,助力生产决策;生成农作物需水预报和灌溉决策方案,完成了远程灌溉目标,并且经过实地试验,验证了自动灌溉的有效性,将灌溉水有效利用系数最高提升了31%以上;形成了大田产业、温室中心、数字科研和区域灌溉等不同专题可视化布局,满足多种农业场景应用需求。为农业生产和跨区域管理提供了便捷工具,为农业灌溉数字化系统搭建和应用提供了参考。

基于天气预报的泾惠渠灌区参考作物滕发量预报模型研究

农业节水背景下,对泾惠渠灌区参考作物滕发量预报方法进行研究,选用Hargreaves-Samani公式作为预报模型,运用中国气象数据网泾河站2008年~2020年13个年份的气象数据进行SPSS参数反演,并采用2022年的实测气象数据进行验证,表明适合泾惠渠灌区的Hargreaves-Samani模型参数为C=0.00122、a=14.19、m=0.259。通过验证,83.2%验证值相对误差在20%以内,同时表明Hargreaves-Samani模型进行参考作物滕发量预报时,呈现“夏季>春季>秋季>冬季”的精度分布规律,可为灌区灌溉预报和智慧水利发展提供实用的理论依据。

高邮灌区参考作物腾发量预报模型研究

【目的】探索高邮灌区的参考作物腾发量(ET_(0))预报方法,提升灌溉预报精度。【方法】基于高邮灌区2003—2017年实测气象数据及2016—2017年气温预报数据,以FAO-56 Penman-Monteith(PM)计算的ET_(0)为基准,将气温预报数据代入率定后的Blaney-Criddle(BC)、Hargreaves-Samani(HS)、McCloud(MC)和简化的PM(PMT)模型,比较不同模型的ET_(0)预报精度。【结果】基于上述4种模型进行ET_(0)预报时,1~7 d预见期的平均均方根误差分别为1.07、1.00、1.16、0.99 mm/d,绝对误差平均值分别为0.85、0.74、0.94、0.75 mm/d,相关系数平均值分别为0.79、0.81、0.76、0.81。【结论】HS和PMT模型的预报精度最好,优于BC和MC模型,MC模型的预报精度最差。建议采用率定后的HS和PMT模型对高邮灌区ET_(0)进行预报。

云南省洱海灌区水稻智能灌溉决策模型研究

提高有效降雨利用率,是节约灌溉用水的重要途径之一。为进一步提高稻田降雨利用率,基于水量平衡原理和作物水分生产函数,结合强化学习方法,构建考虑未来降雨的智能灌溉决策模型。收集了大理站点2012-2020年的实测气象数据和天气预报数据,对智能灌溉决策模型进行训练,将模型应用于云南省洱海灌区。结果表明:洱海地区天气预报存在一定的空报率和漏报率,TS评分较高,降雨预报质量较高。与常规灌溉决策相比,采用强化学习方法的智能灌溉决策,平均每年可以减少灌溉次数0.2次,节约灌水量6.5 mm,节水率为6.0%,提高降雨利用率3.0%,减少排水量6.2 mm,且未造成产量损失。因此,采用智能灌溉决策能在考虑未来天气情况下有效提高降雨利用率,节约灌溉用水,且不造成减产。

不同灌溉方式下无花果需水规律及作物需水量预报

探究不同灌溉方式下无花果需水规律及作物需水量的预报对无花果生产具有重要的研究和指导意义。根据广东省水利重点科研基地2022年5月至2023年12月的无花果种植数据,分析不同灌水方式下无花果需水规律,推求作物系数曲线,结合Hargreaves-Samani模型和单作物系数法,基于公共天气预报进行无花果需水量预报。结果表明:不同灌水方式中沟灌的需水量最大,2023年日均需水量为2.44mm/d,其次是喷灌和地面滴灌,日均需水量分别为2.23mm/d和2.04mm/d,地下滴灌需水量最小,为1.92mm/d,5-9月为无花果需水旺盛期。采用联合国粮农组织(FAO)推荐的单作物系数法推求出试验站无花果Kc作物系数曲线,作物系数地下滴灌<地面滴灌<喷灌<沟灌。气温预报精度较高,最低气温的预报精度优于最高气温的预报精度。经过率定的Hargreaves-Samani模型具有良好的ET0预报精度,相关系数平均值可达0.86。4种灌溉方式无花果作物需水量预报精度低于ET0预报,相关系数范围为0.68~0.74。无花果作物需水量预报模型可以提供未来两周内的无花果需水量,为灌溉决策者提供信息,有利于农民提前安排水资源的分配。

基于5G工业通信技术的智慧果园灌溉系统设计

当前使用的智慧果园灌溉系统,大多通过GPRS(通用分组无线业务)技术传输果园实时用水监测信息,其通信速度存在局限,导致该系统应用后果园灌溉节水率较低,对此,设计基于5G通信技术的智慧果园灌溉系统。在系统硬件方面,完成了数据采集器和手持控制终端的设计。在系统软件方面,构建以内容中心网络为基础的5G分布式无线信息传输体系,快速上传果园监测信息。基于5G通信结构上传的监测数据,结合逐日均值修正法、简化P-M法,进行智慧果园灌水量分析,并基于灌水量分析结果建立动态配水模型,通过模型求解得到智慧果园精准灌溉方案。实验结果表明:该系统应用后果园灌溉节水率最高达到43.16%,满足了智慧灌溉节水要求。