Supply Forecasts Research Articles

Subseasonal to seasonal streamflow forecasting in a semiarid watershed

AbstractOperational streamflow forecasting is critically important to managers of river basins that supply water, hydropower, and flood protection. While seasonal water supply forecasts (WSFs) are important for long‐term water resources planning operations, shorter term (e.g., 1–5 weeks) streamflow forecasts are critical for balancing water conservation with flood risk during wet periods. In this study, we designed a streamflow forecasting system with the water resources group at the Salt River Project (SRP), a provider of water and power to millions of customers in central Arizona (AZ), to provide streamflow forecasts for a diverse and operationally important set of watersheds in AZ. The forecast system uses machine learning to make seasonal WSFs, a rainfall–runoff model driven by ensemble meteorological forecasts to make 35‐day streamflow forecasts, and an innovative approach to improve the WSFs based on the 35‐day streamflow forecasts. This model integration allows for an assessment of the impact of different meteorological forecasts on WSFs, helping SRP to balance water conservation goals with shorter term flood risks. In addition, seasonal WSFs are improved in the early winter when they incorporate the 35‐day streamflow predictions. Furthermore, these improvements are larger than when they incorporate 7‐day streamflow predictions, demonstrating the value of using subseasonal to seasonal (S2S, >1–2 weeks) forecasts to improve seasonal WSFs in these watersheds.

Towards Enterprise Business Management Strategy Based on Big Data Technique

A growing number of commercial economic activities are blooming with continuous economic development of China. Therefore, to improve the effectiveness of commercial economic activities, all aspects must be analyzed and managed to ensure that economic decisions are made scientifically and rationally. With the advent of the information era, competition in the market is intensively happened. Big data has substantially boosted the value of technological systems used in commercial and economic administration. In addition to extracting significant information from big data, it also enables analysis and forecasting of market supply and demand as well as current economic trends, helping companies make decisions about their business and economic management strategies. In the digital era, the emerging technologies represented by big data have been seamlessly integrated into Chinese societal and personal realms, playing an increasingly vital role in enhancing productivity and quality of life. As a consequence, big data systems have also shown greater application value in the business and economic management activities, becoming a key technology that is actively developed and utilised by major companies. It can not only improve the efficiency of data processing and economic management benefits, but also provide reference evidence for enterprise leadership to implement decisions, thereby continuously improving the modern commercial economic management mechanism and enhancing the market competitiveness of enterprises.

Evaluation of Temperature-Index and Energy-Balance Snow Models for Hydrological Applications in Operational Water Supply Forecasts

In the western United States, snow accumulation, storage, and ablation affect seasonal runoff. Thus, the prediction of snowmelt is essential to improve the reliability of water supply forecasts to guide water allocation and operational decisions. The current method used at the Colorado Basin River Forecast Center (CBRFC) couples the SNOW-17 temperature-index snow model and the Sacramento Soil Moisture Accounting (SAC-SMA) runoff model in a lumped approach. Limitations in parameter transferability and calibration requirements for changing conditions with the temperature-index model motivated this research, in which new avenues were investigated to assess and prototype the application of an energy-balance snow model in a distributed modeling approach. The Utah Energy Balance (UEB) model was chosen to compare with the SNOW-17 model because it is simple and parsimonious, making it suitable for distributed application with the potential to improve water supply forecasts. Each model was coupled with the SAC-SMA model and the Rutpix7 routing model to simulate basin snowmelt and discharge. All the models were applied on grids over watersheds using the Research Distributed Hydrologic Model (RDHM) framework. Case studies were implemented for two study sites in the Colorado River basin over a period of two decades. The model performance was evaluated by comparing the model output with observed daily discharge and snow-covered area data obtained from remote sensing sources. Simulated evaporative components of sublimation and evapotranspiration were also evaluated. The results showed that the UEB model, requiring calibration of only a snow drift factor, achieves a comparable performance to the calibrated SNOW-17 model, and both provided reasonable basin snow and discharge simulations in the two study sites. The UEB model had the additional advantage of being able to explicitly simulate sublimation for different land types and thus better quantify evaporative water balance components and their sensitivity to land cover change. UEB also has a better transferability potential because it requires calibration of fewer parameters than SNOW-17. The majority of the parameters for UEB are physically based and regarded as constants characterizing spatially invariant properties of snow processes. Thus, the model remains valid for different climate and terrain conditions for multiple watersheds.

Innovative water rates as a policy tool for drought response: Two case studies from Utah, USA

Drought in the Western U.S. has elevated the need for innovative water pricing. We describe two utilities whose novel pricing structures reflect water availability and reasonable use expectations. One has a physical basis of water rights, landscape water needs, and irrigated area; the other has a hydrologic basis of an annual water supply forecast. Both utilities charge users tiered (increasing block) rates for an adjustable water allotment. The rates have proved hydrologically beneficial, socially equitable, and financially sustainable during the drought, suggesting that water pricing can be an effective policy tool for responsive water management.

Forecast of natural gas supply and demand in China under the background of “Dual Carbon Targets”

As a kind of clean energy which creates little carbon dioxide, natural gas will play a key role in the process of achieving “Peak Carbon Dioxide Emission” and “Carbon Neutrality”. The Long-range Energy Alternatives Planning System (LEAP) model was improved by using new parameters including comprehensive energy efficiency and terminal effective energy consumption. The Back Propagation (BP) Neural Network—LEAP model was proposed to predict key data such as total primary energy consumption, energy mix, carbon emissions from energy consumption, and natural gas consumption in China. Moreover, natural gas production in China was forecasted by the production composition method. Finally, based on the forecast results of natural gas supply and demand, suggestions were put forward on the development of China's natural gas industry under the background of “Dual Carbon Targets”. The research results indicate that under the background of carbon peak and carbon neutrality, China's primary energy consumption will peak (59.4×108 tce) around 2035, carbon emissions from energy consumption will peak (103.4×108 t) by 2025, and natural gas consumption will peak (6100×108 m3) around 2040, of which the largest increase will be contributed by the power sector and industrial sector. China's peak natural gas production is about (2800–3400)×108 m3, including (2100–2300)×108 m3 conventional gas (including tight gas), (600–1050)×108 m3 shale gas, and (150–220)×108 m3 coalbed methane. Under the background of carbon peak and carbon neutrality, the natural gas consumption and production of China will further increase, showing a great potential of the natural gas industry.

Analysis of the Balance between Supply and Demand of Arable Land in China Based on Food Security

Arable land is the natural resource of food production, plays a key role in safe guarding people’s livelihood, maintaining social stability, and ecological balance. In the context of the great challenge of rapid loss of arable land and rapid growth of food demand due to rapid socio-economic development, scientific forecasting of arable land demand and supply, can clarify the conservation pressure of regional arable land, provide a reference for formulating effective arable land policies, and ensuring regional food security and sustainable development. Therefore, with the help of system dynamics model and Gray-Markov model, this study predicts and analyzes the balance of arable land supply and demand in China, and reached the following conclusions. (1) During the projection period, with the continuous development of living standards and agricultural technology, both per capita food demand and food production show an upward trend. However, the combined effects of changes in diet structure and grain yields on changes in arable land demand are smaller than those brought about by population changes. Therefore, the trend of arable land demand is similar to that of population change, and the arable land demand in China reaches a peak of 112.78 million hm2 in 2026. (2) The amount of arable land possession is always greater than the amount of arable land replenishment, and the arable land supply area shows a continuous decreasing trend, and the arable land supply in China is 127.16 million hm2 in 2035. (3) China’s supply holdings are all able to meet the demand of China’s arable land, but combined with existing studies, it is insufficient to meet the demand of crop rotation fallow between 2023 and 2030, which is not conducive to sustainable development. In the future, arable land protection policies should be comprehensively improved and strictly implemented to ensure national food security and achieve sustainable use of arable land.

SNOTEL, the Soil Climate Analysis Network, and water supply forecasting at the Natural Resources Conservation Service: Past, present, and future

AbstractThe Snow Survey and Water Supply Forecasting (SSWSF) Program and the Soil Climate Analysis Network (SCAN) of the United States Department of Agriculture's Natural Resources Conservation Service (NRCS) generate key observational and predictive information for water managers. Examples include mountain climate and snow monitoring through manual snow surveys and the SNOw TELemetry (SNOTEL) and SNOtel LITE networks, in situ soil moisture data acquisition through the SCAN and SNOTEL networks, and water supply forecasting using river runoff prediction models. The SSWSF Program has advanced continuously over the decades and is a major source of valuable water management information across the western United States, and the SCAN network supports agricultural and other water users nationwide. Product users and their management goals are diverse, and use‐cases range from guiding crop selection to seasonal flood risk assessment, drought monitoring and prediction, avalanche and fire prediction, hydropower optimization, tracking climate variability and change, environmental management, satisfying international treaty and domestic legal requirements, and more. Priorities going forward are to continue innovating to enhance the accuracy and completeness of the observational and model‐generated data products these programs deliver, including expanded synergies with the remote sensing community and uptake of artificial intelligence while maintaining long‐term operational reliability and consistency at scale.

Auction Algorithm: Peer-To-Peer System Based on Hybrid Technologies for Smallholder Farmers to Control Demand and Supply

The demand for agricultural goods could be affected by variables such as population growth and consumer tastes. Environmental and zoonotic risks jeopardise crop yields as well as the dependability of distribution and storage networks. Governments can aid in addressing issues of supply and demand by enacting policies like price controls and subsidies. Climate change threatens agricultural output and livestock health, while other climate variables have been polluted by outside sources. Pesticides not only endanger wildlife that isn't intended to be harmed, but they also poison the environment, killing beneficial insects and other organisms. The rising costs of agricultural goods may be mitigated, at least in part, through regional and global trade agreements. When third parties intervene in farming, farmers stand to lose money. One example is the utilisation of low-quality inputs, while another is predatory financing. So we are proposing an Auction Algorithm: peer-to-peer system based on hybrid technologies for smallholder farmers to control demand and supply. To implement an auction algorithm, you need to set up the auction platform and back-end systems. You may also need to integrate the platform with hybrid technologies such as block chain and machine learning. Together, machine learning and blockchain technology can help agriculture companies improve their forecasts of demand and supply, make it easier to keep track of inventory, and reduce risks and inefficiencies in the supply chain. Designing and constructing the blockchain, establishing the P2P network, testing and deploying the system these are the stages of bringing a peer-to-peer system to life using blockchain technology. When we implement the above technologies in the agriculture sector, they have the potential to improve efficiency, promote transparency, and eventually help farmers increase their earnings. This technology can help increase agricultural quality by enhancing industrial efficiency, transparency, and sustainability.

Machine Learning Based Egg Supply Forecasting for Sorting and Grading Institutes

Animal agricultural productivity is highly influenced by the environment with many variables that affect it which makes forecasting a challenging task in this industry. We propose a new and practical approach forecasting egg-supply by utilizing Machine Learning (ML) algorithms, powered by limited data, which is regularly collected in this industry. The proposed approach does not require additional organizational resources for the purpose of collecting information but examines the behavior of farmers as expressed in the supply of eggs to the Egg Sorting Institute (ESI). We propose several possible models and present forecasts for egg supply with 90% accuracy, thus allowing both effective and economical operational decisions to be made.

Spring heat waves drive record western United States snow melt in 2021

Throughout the western US snow melted at an alarming rate in April 2021 and by May 1, hydrologic conditions were severely degraded with declining summer water supply forecasts compared to earlier in the winter. The objectives of this study are to (a) quantify the magnitude and climatological context of observed melt rates of snow water equivalent (SWE) and (b) underpin the hydrometeorological drivers during April 2021 based on atmospheric reanalysis and gridded meteorological data. Peak SWE indicated snow drought conditions were widespread (41% of stations between 5th and 20th percentile) but not necessarily extreme (only 9% of stations less than 5th percentile). Here, using observations from the Snow Telemetry (SNOTEL) network we found record 7 day snow melt rates (median of −99 mm; ±one standard deviation of 61 mm) occurred at 24% of SNOTEL sites and in all 11 Western states. Strong upper atmospheric ridging that began initially in the north Pacific with eastward propagation by mid-April to the Pacific Northwest Coast led to near-surface conditions across the western US conducive to rapid snow loss. One heat wave occurred inland across the Rockies the first week of April and then later in April, a second heat wave impacted the Cascades and northern California. We find that ripening of the snowpack by both record high surface solar radiation and air temperatures were factors in driving the rapid snow melt. Equatorial Pacific sea surface temperatures and the La Niña pattern that peaked in winter along with an eastward propagating and intensifying Madden–Julian Oscillation were likely responsible for driving the placement, strength, and progression of the north Pacific Ridge. This study documents the role of two extreme spring ‘sunny heat wave’ events on snowpack, and the cascading drought impacts which are anticipated to become more frequent in a warming world.

Impact of PV/Wind Forecast Accuracy and National Transmission Grid Reinforcement on the Italian Electric System

The high share of PV energy requires greater system flexibility to address the increased demand/supply imbalance induced by the inherent intermittency and variability of the solar resource. In this work, we have developed a methodology to evaluate the margins for imbalance reduction and flexibility that can be achieved by advanced solar/wind forecasting and by strengthening the national transmission grid connecting the Italian market areas. To this end, for the forecasting of the day-ahead supply that should be provided by dispatchable generators, we developed three advanced load/PV/wind forecasting methodologies based on a chain or on the optimal mix of different forecasting techniques. We showed that, compared to the baseline forecast, there is a large margin for the imbalance/flexibility reduction: 60.3% for the imbalance and 47.5% for the flexibility requirement. In contrast, the TSO forecast leaves only a small margin to reduce the imbalance of the system through more accurate forecasts, while a larger reduction can be achieved by removing the grid constrains between market zones. Furthermore, we have applied the new forecasting methodologies to estimate the amount of imbalance volumes/costs/flexibility/overgenerations that could be achieved in the future according to the Italian RES generation targets, highlighting some critical issues related to high variable renewable energy share.

Supply forecasting and profiling of urban supermarket chains based on tensor quantization exponential regression for social governance.

During the COVID-19 pandemic, the accurate forecasting and profiling of the supply of fresh commodities in urban supermarket chains may help the city government make better economic decisions, support activities of daily living, and optimize transportation to support social governance. In urban supermarket chains, the large variety of fresh commodities and the short shelf life of fresh commodities lead to the poor performance of the traditional fresh commodity supply forecasting algorithm. Unlike the classic method of forecasting a single type of fresh commodity, we proposed a third-order exponential regression algorithm incorporating the block Hankle tensor. First, a multi-way delay embedding transform was used to fuse multiple fresh commodities sales to a Hankle tensor, for aggregating the correlation and mutual information of the whole category of fresh commodities. Second, high-order orthogonal iterations were performed for tensor decomposition, which effectively extracted the high-dimensional features of multiple related fresh commodities sales time series. Finally, a tensor quantization third-order exponential regression algorithm was employed to simultaneously predict the sales of multiple correlated fresh produce items. The experiment result showed that the provided tensor quantization exponential regression method reduced the normalized root mean square error by 24% and the symmetric mean absolute percentage error by 22%, compared with the state-of-the-art approaches.

Investigating the Role of Snow Water Equivalent on Streamflow Predictability during Drought

Abstract Snowpack provides the majority of predictive information for water supply forecasts (WSFs) in snow-dominated basins across the western United States. Drought conditions typically accompany decreased snowpack and lowered runoff efficiency, negatively impacting WSFs. Here, we investigate the relationship between snow water equivalent (SWE) and April–July streamflow volume (AMJJ-V) during drought in small headwater catchments, using observations from 31 USGS streamflow gauges and 54 SNOTEL stations. A linear regression approach is used to evaluate forecast skill under different historical climatologies used for model fitting, as well as with different forecast dates. Experiments are constructed in which extreme hydrological drought years are withheld from model training, that is, years with AMJJ-V below the 15th percentile. Subsets of the remaining years are used for model fitting to understand how the climatology of different training subsets impacts forecasts of extreme drought years. We generally report overprediction in drought years. However, training the forecast model on drier years, that is, below-median years (P15, P57.5], minimizes residuals by an average of 10% in drought year forecasts, relative to a baseline case, with the highest median skill obtained in mid- to late April for colder regions. We report similar findings using a modified National Resources Conservation Service (NRCS) procedure in nine large Upper Colorado River basin (UCRB) basins, highlighting the importance of the snowpack–streamflow relationship in streamflow predictability. We propose an “adaptive sampling” approach of dynamically selecting training years based on antecedent SWE conditions, showing error reductions of up to 20% in historical drought years relative to the period of record. These alternate training protocols provide opportunities for addressing the challenges of future drought risk to water supply planning. Significance Statement Seasonal water supply forecasts based on the relationship between peak snowpack and water supply exhibit unique errors in drought years due to low snow and streamflow variability, presenting a major challenge for water supply prediction. Here, we assess the reliability of snow-based streamflow predictability in drought years using a fixed forecast date or fixed model training period. We critically evaluate different training protocols that evaluate predictive performance and identify sources of error during historical drought years. We also propose and test an “adaptive sampling” application that dynamically selects training years based on antecedent SWE conditions providing to overcome persistent errors and provide new insights and strategies for snow-guided forecasts.

Establishing Opportunities and Limitations of Forecast Use in the Operational Management of Highly Constrained Multiobjective Water Systems

The potential utility of forecast information to improve reservoir control is well established, but physical, operational, and institutional constraints inhibit the full realization of these benefits. To help integrate forecast technology into operational water management, it is necessary to establish the opportunities and limitations of forecast use within the current system management framework, so that water managers and planners can identify in practice what constraints or aspects of control policy design most limit forecast utility. In this work, we explore the value of forecasts in the current outflow management plan of the Lake Ontario-St. Lawrence River basin, which is the first regulation policy of this system to use water supply forecasts to guide release decisions. We assess the value of forecasts for many-objective system management (e.g., upstream and downstream flood risk reduction, hydropower production, commercial navigation costs, recreational boating benefits, and wetland restoration), as a function of forecast accuracy, timing, and interactive effects, with system constraints and control rule structures. Results show that a 20%–30% reduction in forecast error over current statistical forecasts leads to observable improvements in most objectives, which grow significantly with additional forecast accuracy. Realizing these benefits is possible by increasing forecast accuracy, particularly in the springtime when tradeoffs between objectives are the greatest. However, we also identify one objective (wetland restoration) that declines with improved forecast skill, as well as operational constraints that limit forecast utility under the current outflow management plan. Overall, these results suggest that key aspects of the current control policy could be revised to better utilize forecast information, especially as forecasts improve over time.

Large-Scale Scheduling Model Based on Improved Ant Colony Algorithm

With the rapid development of the city, shared bicycle travel has also entered a stage of rapid development. In order to ensure the happiness of citizens traveling, in view of the current supply and demand resources and bicycle scheduling problems, a model of supply and demand resource forecasting and multisite and multivehicle scheduling are established. Supply and demand resource prediction uses characteristic variables based on the graph structure itself as input variables of the prediction model XGBoost (extreme gradient boosting). Combined with the actual situation, the improved ant colony algorithm is used to design a reasonable scheduling for the multisite and multivehicle routing problem (VRP). Using Xiamen City shared bicycle data for simulation training, the results show that the shared bicycle scheduling method proposed in this paper has strong robustness and rationality.

Simplified Cross‐Validation in Principal Component Regression (PCR) and PCR‐Like Machine Learning for Water Supply Forecasting

AbstractCross‐validated principal component regression (PCR) is widely used in day‐to‐day operational forecasting systems for seasonal river runoff volume in western North America. Complexities are increasing in both predictor datasets (including climate‐science products) and in predictive models employed instead of linear regression within the PCR framework (including artificial intelligence), potentially complicating cross‐validation for model evaluation. We explored these issues with 300 modeling experiments on two high‐impact and hydroclimatically diverse basins in the western United States, the Truckee River (Sierra Nevada) and Rio Grande headwaters (southern Rockies), using five different PCR and PCR‐like machine learning models. The results suggest out‐of‐sample error is satisfactorily estimated by applying cross‐validation to only the final, supervised learning, step of PCR/PCR‐like procedures. The outcome facilitates streamlined algorithms and potentially reduced computational times for more complex emerging model architectures and datasets; provides reassurance around a possible inability to perform genuinely complete cross‐validation when predictors include certain complex and externally sourced data sources; and may reflect mitigation of overtraining by geophysical process‐informed model development protocols normally used during feature selection in operational water supply forecast (WSF). The results provide practical guidance helping support the design of next‐generation WSF models.

Research on Energy Supply and Demand Forecast and Carbon Neutralization Path Based on Grey-Monarch Butterfly Optimization Model

Energy and electricity are the key areas for China to achieve the double carbon target, and accurate forecasting of future energy supply and demand and carbon emissions is beneficial to develop a feasible path for low carbon transition. The gray prediction model GM (1, 1) is one of the most widely used dynamic prediction models in the field of energy forecasting, but it requires high raw data and the model may fail when the development coefficient of GM (1, 1) is large. On the other hand, the gray action of GM (1, 1) directly determines the model prediction accuracy, this paper introduces a novel population intelligence algorithm monarch butterfly optimization (MBO), which has excellent performance in practical optimization problems, into the optimization process of gray action of GM (1, 1), and proposes a new Gray-Monarch Butterfly optimization prediction model to realize the prediction. By comparing the prediction data with the classical literature, the effectiveness and superiority of the proposed Gray-monarch butterfly optimization prediction model are confirmed.Finally a carbon neutral pathway is given for Tianjin based on the prediction results.

A Comprehensive Analysis of the Power Demand–Supply Situation, Electricity Usage Patterns, and the Recent Development of Renewable Energy in China

Renewable energy is now the world’s most reliable and sustainable solution to environmental pollution, the energy crisis, and social sustainability. In order to regulate renewable energies and ensure the sustainable development of renewable energy in China, a regulatory framework is imperative. Electricity demand and supply forecasting have become one of the most important topics for research on sustainable solutions to energy issues. This article analyzes the Chinese electric power industry structure by looking at historical electricity demand and supply data. This study shows how a divergent set of energy policies can facilitate the application of renewable energy to China’s electric power sector. The analysis shows that in 2020, China’s electricity generation and consumption increased by 0.9 and 1.3 percent annually, respectively, producing capacity of power plants increased by 5.6 GW, coal consumption of power supply decreased by 4.3 g/kWh, power generation projects investment increased by 51.6 billion RMB, power grid projects investment decreased by 1.8 billion RMB, and newly installed generation capacity increased by 769 GW year on year (YOY). During the first three quarters of 2021, the generation, consumption and coal consumption of electricity increased respectively by 10.7 and 12.9%, the generating capacity of power plants increased by 9.4 GW, the average coal consumption of power supply decreased by 0.9 g/kWh, power generation projects investment increased by 1.8 billion RMB, while power grid projects investment decreased by 0.3 billion RMB and new generation capacity added around 20.16 GW compared to the same period last year. Furthermore, domestic power consumption grew by 6.0% and 7%, respectively, in 2020–2021. The paper examines China’s current climate, developments, and renewable energy targets between 2020 and 2021. This research aims to identify the main risks associated with China’s renewable energy development and propose a few policy measures for risk management.

Between Biodiversity Conservation and the Supply for Broadleaved Wood: A Case Study of State Forests National Forest Holding (Poland)

Climate change is an important issue that increasingly affects our lives. One of the proposals for mitigating climate change is fighting biodiversity loss, which can support climate mitigation and adaptation actions. In Poland, the possibility of excluding large tracts of forest areas from use is being considered. The discussed the exclusion of forest land from use will affect the timber supply and market, especially for broadleaved wood. The main purpose of this analysis is to present a timber supply forecast, with a particular focus on the possibility of obtaining broadleaved hardwood timber in Poland from forests managed by State Forests National Forest Holding under three scenarios that assume different criteria for selecting forest areas for protection. The work was divided into two main phases: (1) the analysis of historical sales volume of wood products and average sale prices of hardwood during the period 2011–2020; (2) the preparation of a forecast of the potential possibility of maintaining broadleaved hardwood production in the three decades between 2020 and 2049. In the forecast, it was assumed that about 2.7 million hectares of planted and production forests are excluded from use in order to implement the provisions of the 2030 Biodiversity Strategy. In Scenario “I”, the supply of merchantable broadleaved roundwood volume will be reduced to 14%–18% that of Scenario “0”. In Scenario “II”, 55% of the “0” scenario is harvested, and in Scenario “III”, 33%–37% of the “0” scenario merchantable broadleaved roundwood is harvested. The introduction of restrictions on timber harvesting as a result of Poland’s compliance with European Union requirements in the area of environmental protection will lead to a significant reduction in the supply of timber on the market. This may lead to a further increase in timber prices and an increase in the importance of large timber buyers at the expense of local buyers. The recommendations contained in the policy objectives that the EU sets for the states should be supported by a thorough analysis when selecting areas for strict protection.

Forecast of Grain Supply and Demand in Jiangsu Province and Analysis of Its Influencing Factors-- based on Spatial Panel Model and ARIMA-GM Joint Model

To analyze the influencing factors of grain yield change at present stage and predict the possible grain problems in Jiangsu province is not only beneficial to explore the development trend of grain problems in Jiangsu Province, but also can provide theoretical basis for the government's grain production decision-making. This article selected cities in Jiangsu province in 2001-2020 food production and its related influencing factors of data, the first structure, spatial panel data model to analyze the indexes which influence the production of food, and then through the ARIMA - GM joint model changes of grain production in Jiangsu province in the next five years to forecast, and comparing the future population forecast data of Jiangsu province, To study the change of grain supply and demand and potential problems in Jiangsu province in the next five years. The results show that agricultural technical efficiency, land scale management and effective labor input are the important factors restricting grain yield at present. At the same time, through the prediction of grain output, combined with the forecast results of population in Jiangsu Province, and compared with the growth rate, it can be seen that the growth rate of grain output in the highly developed areas of Jiangsu province, such as Nanjing, Suzhou, Wuxi and other cities, is far less than the growth rate of population. It can be seen that in some areas of Jiangsu Province in the next few years, the problem of grain supply and demand may gradually become prominent, become the "heart trouble" restricting economic development. Finally, some feasible suggestions are put forward for the possible grain production problems in Jiangsu Province.