Planning Model Research Articles

Portfolio Agriculture: A Model for Resilient Regional Agricultural Planning

Food security is threatened by climate change worldwide; consequently, agriculture and farming livelihoods must adapt to new and unpredictable conditions. These conditions vary along spatial scales, and since agricultural yields are sensitive to microclimate conditions, a locally tailored data-driven approach may be helpful. Furthermore, limited agricultural resources like water and labor increasingly constrain food production. This research proposes a regional portfolio model for identifying crop choices and regional portfolio compositions that align with known and forecasted microclimate variation in temperature and humidity. The model will enable farmers to assess tradeoffs between the financial returns and agricultural production risks. The goal of this work is to provide new insights into agricultural planning in the face of climate risk and limited access to water and labor resources. Three steps are taken. Firstly, regional agricultural land is divided into farming subunits, with each representing a terroir characterized by temperature and humidity. Then a simulated yield coefficient is used to assess the effect of microclimate variables on the yield of the different crops in the portfolio of each subunit. Secondly, farming resource allocation, represented by water and labor, across crops and farming subunits is optimized to maximize the yield and associated financial return from farming across the agricultural region. Finally, a resilient agricultural planning model is developed based on the assumed data for regional microclimate and agricultural resources. The results of this research can be used by regional farmers as a reference for selecting crop portfolios and resource allocations to maximize overall profit.

Modeling and scenario building for climate change adaptation planning: The case of large mining in Chile

The mining sector in Chile is a strategic industrial sector for the country. Existing evidence shows that it faces several serious climate change threats; precipitation and flooding, droughts, heatwaves, among others. This scene put pressure on the government and the industry to develop efficient adaptation plans. To date, adaptation plans are designed under the rather linear paradigm of predict-then-act or the impact-lea approach as they are characterized in the IPCC Assessment Report 5 (AR5). Literature and the IPCC reports have identified the limits of those planning paradigms showing the relevance of adaptation barriers or enabling conditions, which should be considered as intrinsic part of the planning problem.In methodological terms, planning for climate change risks implies an enriched adaptation plan problem, previously characterized only by an operative climate risk management, that must be described at the beginning of the decision-making process. In this study, our objective is to contribute to the climate change adaptation planning of large-scale mining in Chile. The study is based on a climate change adaptation planning approach that overcomes the limitations of the current paradigm. In doing so, we start from the understanding that what emerges as an object of analysis from adding to the climate risks their enabling managing conditions is a social system. The social system whose function is that social climate risk management takes place. Therefore, we call it the Social Management System for Adaptation to Climate Change (SMSACC). As such the SMSACC should be the adaptation planning key object.In the first place we modeled that system applying a qualitative system methodology and then we developed it into a mathematical model based on graph theory, in particular the signed digraphs. This allows us to simulate two types of intervention on the enlarged object of analysis of the large mining adaptation plan. On the one hand, we carried out a future scenario analysis based on prospective tools which enables us to understand the system's answer to different future behavior of its environment, including climate change. On the other hand, we simulate different strategic interventions options on the system, which facilitates understanding the system's reaction under different public policy approaches.The modeling and simulation results provided an insightful understanding of the dilemma of social adaptation management of large mining in Chile, and as such they are useful input for the planning process.

Location and Size Planning of Charging Parking Lots Based on EV Charging Demand Prediction and Fuzzy Bi-Objective Optimization

The market share of electric vehicles (EVs) is growing rapidly. However, given the huge demand for parking and charging of electric vehicles, supporting facilities generally have problems such as insufficient quantity, low utilization efficiency, and mismatch between supply and demand. In this study, based on the actual EV operation data, we propose a driver travel-charging demand prediction method and a fuzzy bi-objective optimization method for location and size planning of charging parking lots (CPLs) based on existing parking facilities, aiming to reduce the charging waiting time of EV users while ensuring the maximal profit of CPL operators. First, the Monte Carlo method is used to construct a driver travel-charging behavior chain and a user spatiotemporal activity transfer model. Then, a user charging decision-making method based on fuzzy logic inference is proposed, which uses the fuzzy membership degree of influencing factors to calculate the charging probability of users at each road node. The travel and charging behavior of large-scale users are then simulated to predict the spatiotemporal distribution of charging demand. Finally, taking the predicted charging demand distribution as an input and the number of CPLs and charging parking spaces as constraints, a bi-objective optimization model for simultaneous location and size planning of CPLs is constructed, and solved using the fuzzy genetic algorithm. The results from a case study indicate that the planning scheme generated from the proposed methods not only reduces the travelling and waiting time of EV users for charging in most of the time, but also controls the upper limit of the number of charging piles to save construction costs and increase the total profit. The research results can provide theoretical support and decision-making reference for the planning of electric vehicle charging facilities and the intelligent management of charging parking lots.

Trajectory optimization and stability control for a novel unmanned intelligent wheel-legged vehicles on unstructured terrains

The trend of intelligent vehicles is currently expanding, and a new class of unmanned intelligent vehicles known as wheel-legged vehicles (WLVs) is emerging. WLVs excel in transportation on unstructured terrain by offering a unique combination of the efficiency of wheels on flat ground and the versatility of legs to tackle obstacles. To enhance the locomotion performance of WLVs on unstructured terrains, this paper presents a novel framework for improving their locomotion through nonlinear programming-based (NLP) trajectory optimization and stability control. The framework optimizes the vehicle’s body and wheel positioning while incorporating terrain information and employs a linear rigid body dynamic model for efficient motion planning. The stability control framework combines feedforward control using ground reaction forces with feedback control through joint PD control and utilizes model predictive control (MPC) to adjust the wheel slip ratio to prevent slip on steep slopes. Experimental validation on the real vehicle with torque-controlled wheels demonstrated the capability of driving over a 1 m height with a 30°slope at an average speed of 0.7 m/s and a maximum speed of 1.03 m/s. Our approach also enables the WLV to overcome obstacles, such as inclines, while dynamically negotiating these challenging terrains.

Review of research on disaster mitigation emergency congregate shelter planning for vulnerable group

The elderly, including individuals with disabilities, women, and children, among other vulnerable evacuees, are the most fragile group during disasters. During major disasters, safely and rapidly transferring vulnerable evacuees to shelters that can meet their sheltering needs is crucial and challenging in emergency rescue work. This article systematically analyzes the sheltering behavior characteristics and sheltering needs of vulnerable evacuees based on relevant research at home and abroad. It also reviews the technical indicators and requirements for emergency shelter planning for vulnerable evacuees, and studies emergency shelter planning models from the perspective of vulnerable evacuees. Finally, it proposes prospects for emergency shelter planning indicators and models based on vulnerable evacuees, providing a reference and guidance for improving and enhancing emergency sheltering strategies for vulnerable evacuees.

Planning for complex inferior vena cava filter retrievals: the implementation and effectiveness of 3D printed models

BackgroundInferior vena cava filter (IVC) retrieval is most often routine but can be challenging with high morbidity in complex cases, especially those with an extended dwelling time. While risk of morbidity in complex retrievals is decreased with advanced filter retrieval techniques, deciding when and which to use these requires detailed pre-procedural planning. The purpose of our study was to evaluate patient-specific 3D printed anatomic IVC filter models for aiding complex IVC filter retrievals.MethodsAll IVC filter retrieval patients between June 2021 and September 2022 at one academic medical hospital were prospectively screened. Nine met criteria for complex retrieval, and their CT images were used to 3D print patient-specific IVC and filter models. Models were used in pre-procedural planning and clinical utility was assessed using the Anatomic Model Utility Likert Questionnaire and estimations of the procedural and fluoroscopy time saved.ResultsThe usage of 3D printed models in pre-procedural planning had high clinical utility based on the Likert questionnaire (Anatomic Model Utility Points 366.7 ± 103.1). Using a model significantly increased confidence in planning (p = 0.03) and modified the treatment plan in seven cases. It also led to cost-efficient use of resources in the procedure suite with estimated reduction in procedure and fluoroscopy time of 29.0 [20.3] (p = 0.003) and 10.2 [6.7] (p = 0.002) minutes, respectively.Conclusion3D printed anatomic models for patients who require complex IVC filter retrieval demonstrated Likert-based high clinical utility and led to estimated reductions of procedural and fluoroscopy time.

CureMate: A clinical decision support system for breast cancer treatment

BackgroundBreast Cancer (BC) poses significant challenges in treatment decision-making. Multiple first treatment lines are currently available, determined by several patient-specific factors that need to be considered in the decision-making process. PurposeTo present CureMate, a Clinical Decision Support System to predict the most effective initial treatment for BC patients. Different artificial intelligence models based on demographic, anatomopathological and magnetic resonance imaging variables are studied. CureMate’s web application allows for easy use of the best model. MethodsA database of 232 BCE patients, each described by 29 variables, was established. Out of four machine learning algorithms, specifically Decision Tree Classifier (DTC), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (K-NN), and Support Vector Machine (SVM), the most suitable model for the task was identified, optimized and independently tested. ResultsSVM was identified as the best model for BC treatment planning, resulting in a test accuracy of 0.933. CureMate’s web application, including the SVM model, allows for introducing the relevant patient variables and displays the suggested first treatment step, as well as a diagram of the following steps. ConclusionThe results demonstrate CureMate’s high accuracy and effectiveness in clinical settings, indicating its potential to aid practitioners in making informed therapeutic decisions.

Optimization of shared energy storage configuration for village-level photovoltaic systems considering vehicle charging management

Distributed renewable energy is more abundant in rural areas, and a large amount of distributed photovoltaic grid-connected power brings challenges to the stable of the power grid. How to promote the self-generation and self-consumption of distributed renewable energy has become an urgent problem. In this paper, a village-level distributed photovoltaic power generation system including energy storage and electric vehicles is constructed. With the goal of minimizing the photovoltaic grid-connected power and maximizing the annual comprehensive revenue, the planning model of energy storage capacity allocation for village-level distributed power generation system is constructed. Considering the charging management for different numbers of electric vehicles, the optimal energy storage capacity allocation strategy is solved using the improved particle swarm algorithm.Five scenarios are set up as examples to be analyzed.The conclusions are:(1)After the configuration of a reasonable energy storage,the grid-connected generation of the system is significantly reduced,and the annual comprehensive revenue of the system is significantly increased.(2)After considering charging management for different numbers of electric vehicles, the capacity and power of the energy storage configuration can be significantly reduced, thus reducing the energy storage investment cost and operation and maintenance cost, and further significantly improving the annual comprehensive revenue of this system.

Digital twin-based multi-granularity synchronisation for production-warehousing under batch processing mode

Batch production is a cost-effective way that boosts efficiency in manufacturing systems. As customer demands become increasingly customised, there is a growing need to consolidate numerous small-batch orders. However, if batch production exceeds the optimal level, it may lead to the premature completion of customer orders, causing temporary congestion in the finished goods warehouse and prolonged resource occupation. Consequently, an essential focus of this study pertains to coordinating decision-making units like workshops and warehouses within batch production setups to ensure stable system operation amidst dynamic customer demands. The proposed solution encompasses a Digital Twin-based Multi-level Synchronised Control System (DTMCS) framework, featuring the Multi-granularity Synchronised Control Mechanism (MgSCM) and a collaborative optimisation model for batch production and warehouse planning. By examining a practical case study from a paint manufacturing company, the research delves into the effects of four synchronised control patterns on various system performance metrics, such as operating costs, equipment and warehouse utilisation rates, and system stability. Overall, this study provides an adaptable and cost-effective solution for enhancing production-logistics synchronisation.

A planning framework for intra-city electric bus road transportation systems

Gasoline-based vehicle transportation plays a crucial role in environmental pollution, which eventually leads to serious health issues in urban areas. The scope of large-scale deployment of personalized electric vehicles in the near future can lean toward such issues but can overburden local distribution grids (LDGs), and the entities are producing green energy. In this context, an electric bus road transportation system (EBRTS) can be seen as an effective and promising way, although it is capital-intensive. EBRTs can be successfully deployed by developing a well-tailored planning model that encompasses amicable solutions while considering the conflicting interests of electric utilities and investors/transporters.This paper proposes a planning model for intra-city EBRTS, especially for metropolitan cities, to extract tangible benefits in favour of electric utilities and private players. The proposed framework envisages a bus fleet charging model and financial model within the spatial, technical, and financial constraints yet preserves the interests of electric utilities and investors by providing tentative solutions with all information necessary from the investor’s perspective. The methodology is free from optimization as the realistic constraints inherently employ search space reduction. The simulation results on a real public transportation system reveal the proposed methodology’s simplicity, rationality, applicability, and flexibility.

Impact of a care delivery intervention for patients with socioeconomic disadvantages, in their preferred language of English or Spanish.

97 Background: Sinai Health System’s oncology program serves Chicago’s inner city patients with substantial needs for social and primary care, many of whom prefer communication in Spanish. Sinai has implemented a care delivery intervention to address these needs, using the 4R Oncology Model for patient-facing care planning and patient self-management. 4R (Right Info/Care/Patient/Time) has shown significant improvements in the timeliness of care cancer delivery and referrals to cancer care (1). Herein, we implemented the 4R intervention to improve the timeliness of care delivery and referrals to care, focusing on the social and primary care needs of Sinai patients. Methods: Evaluation was conducted by surveying historical control and intervention (4R) cohorts of patients in their preferred language of Spanish or English. The 4R cohort received care at a Sinai medical oncology clinic Apr 2023 - Jan 2024. Control cohort received care Jan 2023 – March 2023. Analyses were conducted using Fisher’s exact test. Results: Survey response rates: 76% (38/50) in control and 75% (33/44) in 4R cohorts. Participant characteristics were comparable between control and 4R cohorts, respectively: 55%, 58% Hispanic, 42%, 39% Black; 76%, 82% high school education or less; 87%, 97% < 30k income; 50%, 55% preferred language Spanish; 47%, 45% English. For the total cohorts, all 5 metrics improved between control and 4R, and 4 of the 5 metrics improved significantly (Table). Among Spanish-preferred patients, 3 of the 5 metrics improved significantly, while improvements among English-preferred patients were not statistically significant. Both language groups saw numerical, but not statistically significant improvement in receiving referrals to primary care and meeting all their practical and family needs. Conclusions: The 4R Oncology intervention resulted in significant improvement in time to treatment and referrals to social and primary care in our population of socioeconomically disadvantaged patients with high needs for these services. Patients preferring Spanish benefited at a higher rate than English-preferring patients, indicating that 4R may be an effective method to address the needs of this important patient group. Future efforts will further optimize 4R to address remaining gaps for this group, as well as to improve the delivery of this care for the English-preferred patients. 1. Trosman JCO OP 2021. Metric Control Total %N=38 4R Total %N=33 Control Spanish %n=19 4R Spanish %n=18 Control English %n=19 4R English %n=15 Started treatment within 6 weeks of diagnosis 61 88* 53 94* 68 80 Received referral to primary care 66 82* 74 83 58 80 Received referral to support for transportation, food, and other needs 68 85* 63 89* 74 80 Referred to help and resources to help pay for care 50 67* 47 78* 53 53 All of my practical and family needs were addressed 86 89 84 89 87 87 *p<0.1 comparing control and 4R cohorts.

Incorporating Complexity and System Dynamics into Economic Modelling for Mental Health Policy and Planning.

Care as usual has failed to stem the tide of mental health challenges in children and young people. Transformed models of care and prevention are required, including targeting the social determinants of mental health. Robust economic evidence is crucial to guide investment towards prioritised interventions that are effective and cost-effective to optimise health outcomes and ensure value for money. Mental healthcare and prevention exhibit the characteristics of complex dynamic systems, yet dynamic simulation modelling has to date only rarely been used to conduct economic evaluation in this area. This article proposes an integrated decision-making and planning framework for mental health that includes system dynamics modelling, cost-effectiveness analysis, and participatory model-building methods, in a circular process that is constantly reviewed and updated in a 'living model' ecosystem. We describe a case study of this approach for mental health system policy and planning that synergises the unique attributes of a system dynamics approach within the context of economic evaluation. This kind of approach can help decision makers make the most of precious, limited resources in healthcare. The application of modelling to organise and enable better responses to the youth mental health crisis offers positive benefits for individuals and their families, as well as for taxpayers.

Investigating the efficacy of a fast urban climate model for spatial planning of green and blue spaces for heat mitigation

Problems caused by urban heat have prompted the exploration of urban greenery and blue spaces for heat mitigation. Various numerical models can simulate heat-related processes, but their use as support-tools to urban planners remains underexplored, particularly at the city-scale, due to high computational demand and complexity of such models. This study investigates the spatial relationships between urban heat, urban form and urban green and blue spaces with the fast climate model TARGET (The Air-temperature Response to Green/blue-infrastructure Evaluation Tool), which only requires minimal inputs of standard meteorological data, land cover and building geometry data. Using the City of Zurich as our case study, we: (i) validated the TARGET model against air temperature measurements from private sensor networks, (ii) performed a sensitivity analysis to identify key variables affecting urban heat, and (iii) investigated urban heat relationships with blue-green cover at locations frequented by pedestrians. Presence of urban green and blue spaces across the region shows potential for reducing local air temperatures by up to 5.2 °C (with urban forest). Investigating this relationship at different locations in the city revealed key districts that should potentially be targeted for reduction of pedestrian heat-impacts, due to their high pedestrian traffic, fewer green and blue spaces and high daytime air temperatures. Our results not only provide insights into the cooling effect of different amounts of green and blue features in the urban environment, but also demonstrates the application and integration potential of simplified models like TARGET to support the planning of more liveable future cities.

Coupled Tanks Level Control Based on Volume Balance Method

Abstract The laboratory bench “Coupled tanks” represents a model of real technological plans where the levels and flow rates of liquids must be controlled. Such training benches are very common and there is a very large number of publications related to their control. All publications work with a non-linear model based on the Bernoulli equation for ideal fluids, which is non-linear – the square root of the fluid height is present. This equation or system of equations is linearized and attempts are made to control such systems by means of linear models. This article shows that this approach is not correct and proposes a completely different one based on the volume balance method.

Coordinating expensive, difficult-to-obtain prophylactic medications before discharge: A quality improvement project in an academic stem cell transplant unit.

337 Background: Infections are a significant source of morbidity/mortality in allogeneic stem cell transplant (alloSCT) patients and antimicrobial prophylaxis has reduced deaths. Between July 2022 and July 2023, 21% of new alloSCT recipients were discharged from UVA Medical Center without posaconazole or isavuconazonium +/- letermovir in-hand at the time of hospital discharge necessitating daily oral drug administration at the infusion center until medication could be obtained. This led to excess cost for UVA, burden on clinic staff, missed doses, and patient frustration. We sought to decrease the number of new alloSCT recipients discharged without appropriate prophylaxis in-hand from 21% to 10% by November 2024. Methods: Per the 2023 ASCO Quality Training Program associated with this project, a Model for Improvement and Plan Do Study Act (PDSA) methodology was utilized. The population included alloSCT patients with new prescriptions (Rxs) for posaconazole or isavuconazonium +/- letermovir. The outcome measure was percentage of newly discharged alloSCT patients requiring oral prophylaxis at the infusion center. The process measure was Time to Affordable Medication (TAM) defined as days from Rx prior-authorization (PA) request to paid claim with an affordable copay (defined as a copay the patient was able/willing to pay, including free drug approvals or assistance programs). The counter measure consisted of initiating the Rx PA process 10 days prior to planned admission via a discharge test Rx order set instead of waiting until admission. This standardized process allowed for clearer communication and more time for pharmacy technicians to process the Rx for PA, copays, free drug applications, and pharmacy logistics. Upon admission, the official Rx was released to the discharge pharmacy. If Rx shipment was required, this was set up the week prior to discharge. An I-chart (3-sigma) statistical process control (SPC) chart was used to assess the intervention. Results: The baseline TAM was assessed retrospectively in 22 Rxs over 3 months prior to intervention for a mean of 7.5 days. PDSA cycle 1 was implemented Nov. 2023. TAM for the first 35 Rxs was 4.3 days and the SPC upper control limit decreased from 26.3 days to 13.3 days demonstrating overall markedly decreased variation despite data from early 2024 having greater variability due to new insurance deductibles. Rxs requiring 10 or more days were due to free drug application processes. Importantly, no newly discharged alloSCT patients have required drug administration at the infusion center. Conclusions: PDSA #1 resulted in a decrease in TAM of 3.2 days, decreased variation in the process, and no patients discharged without drug in hand. Since we have already surpassed our aim, next steps include demonstrating sustainability of the process and a survey requesting feedback to identify balance measures.

A novel two-stage optimal layout model of hydrogen refueling facility network based on green electricity hydrogen production: Beijing-Tianjin-Hebei region of China as case study

Green electricity hydrogen production(GEHP) is fundamental support for developing new-type power system and achieving the green and low-carbon transformation in the transportation sector. It is key issue to build a hydrogen refueling facility network(HRFN) to link hydrogen production and consumption. Firstly, the framework of HRFN is proposed including hydrogen production points(HPP), hydrogen refueling stations(HRS) and hydrogen demand points(HDP). Secondly, a two-stage model is built. In the first stage, the siting model of HRS cluster is constructed considering the service capacity, service radius, and construction, operation and penalty costs. In the second stage, the bi-objective planning model of HRFN is constructed considering network stability, hydrogen storage and transportation forms and producing total costs. Finally, the Beijing-Tianjin-Hebei region of China(BTH) is taken as case study to verify the effectiveness. Sensitivity analyses are conducted on four factors:HRSs’ service radius, service capacity, GEHP’s efficiency and HDPs’ scope. The key findings are: 1)the service radius and capacity of HRSs and HDPs’ scope all affect the layout of HRSs, with HDPs’ scope further influencing HPPs’ number; 2)the construction and operation costs are more impacted by changes in GEHP's efficiency compared to network stability;3)the network should be strengthened to cover the whole processes from hydrogen production to consumption.

Net-zero carbon emission oriented Bi-level optimal capacity planning of integrated energy system considering carbon capture and hydrogen facilities

The integrated energy system (IES) is considered an efficient energy provision paradigm to improve the utilization efficiency of renewable generation (RG), reduce energy cost and improve energy supply reliability. However, the multi-dimensional uncertainties and the hydrogen utilization have posed enormous challenges to the optimal planning of the IES. This paper proposes a net-zero carbon emission oriented bi-level optimal planning model for the IES with full consideration of the multiple operational uncertainties in the IES (RG, multiple demands). The upper level is an optimal capacity configuration model, and the economic costs, energy selling profits, the penalty for power abandonment and energy supply shortage are settled as the objectives. The lower level is an optimal energy dispatch model with the objective function of minimizing the total operating cost of the IES on typical days. An integrated energy system framework consisting of multiple energy flows is formulated in the presence of carbon capture system (CCS) and hydrogen-to-power (H2P) facilities. To fully characterize the uncertainties of RG and multiple demands, a data-driven scenario generation method is adopted to expand the operational scenarios, in which probability distribution assumptions and prior knowledge are not necessary. Finally, the effectiveness of the proposed solution is extensively demonstrated through numerical simulation, and a sensitivity analysis is carried out to assess the impact of changes in electricity and gas prices on the IES planning results.

Optimal Design of Wind-Solar complementary power generation systems considering the maximum capacity of renewable energy

This paper proposes constructing a multi-energy complementary power generation system integrating hydropower, wind, and solar energy. Considering capacity configuration and optimization of the complementary power generation system, a dual-layer planning model is constructed. The outer layer aims to maximize the accessible scale of wind and solar energy, while the inner layer considers the matching degree between power output and grid load. The optimization uses a particle swarm algorithm to obtain wind and solar energy integration's optimal ratio and capacity configuration. The results indicate that a wind-solar ratio of around 1.25:1, with wind power installed capacity of 2350 MW and photovoltaic installed capacity of 1898 MW, results in maximum wind and solar installed capacity. Furthermore, installed capacity increases with increasing wind and solar curtailment rates and loss-of-load probabilities. When the loss-of-load probability is set to 3 %, the impact of wind and solar curtailment rates on the installed capacity ratio is relatively small. The complementary characteristics of wind and solar energy can be fully utilized, which better aligns with fluctuations in user loads, promoting the integration of wind and solar resources and ensuring the safe and stable operation of the system.

Enhancing crop production in the Haihe Basin while addressing challenges related to water quantity and quality

To tackle the challenge of ensuring food security while managing water availability and quality constraints in the Haihe Basin, a critical grain-producing region in China with a dense population and severe water degradation issues, we have developed a comprehensive spatial optimization (CSO) strategy. This approach integrates various crop and soil management practices, land consolidation, and cutting-edge breeding technologies. It also uses a spatial planning model based on linear programming, considering water quantity and quality constraints. Our research shows that crop yields may drop by 14 % (3780 Kt) compared to levels in 2017 due to restrictions on groundwater extraction and nitrogen (N) concentrations in leaching or runoff. However, by strategically maximizing overall crop yields through the integrated CSO strategy without changing the crop production structure, the total crop yield could potentially increase by 81 % (21,817 Kt) while using 3.0 % (86 Kha) less cultivated land than in 2017. This would help to fulfill the projected food demand in 2050. If the integrated aims to minimize the sown area after fulfilling the demand for crops in 2050, around 28 % of the sown area, or 820 Kha cropland, could be reduced compared with 2017. This reduction may save more land for natural conversation. Furthermore, total N losses, including ammonia, nitrous oxide emissions, runoff, and leaching, could be reduced by 23 %–43 % (139–252 Kt), depending on the specific optimization strategy goals. The stepwise integrated optimization strategy provides a feasible framework for the Haihe Basin, enabling the maintenance or even enhancing current crop yields while safeguarding water quality and quantity.

Learning to construct a solution for UAV path planning problem with positioning error correction

Unmanned aerial vehicles (UAVs) are advanced flight systems. However, their positioning systems cause distance-dependent errors during flight. This study seeks to solve the UAV path planning problem with positioning error correction (UPEC) with an end-to-end method. Traditional methods struggle to balance solution quality and computational overload, and often have limited utilisation of scenario information. To overcome these issues, we propose a path planning model (PPM) based on deep reinforcement learning to solve the UPEC. The model has a complete structure that includes a mathematical model, feature engineering, solution process, neural policy network, scenario generation, training process, and test solution mechanism. Specifically, we first establish a Markov decision process (MDP) for UPEC and apply feature engineering with effective features to support decision-making. We then introduce a path planning neural network (PPNN) to represent the MDP policy. Based on the dataset generated from the multi-rule combination validation, we train the PPNN using the proposed RL algorithm with storage pool. Furthermore, we propose a backtracking mechanism to guarantee solution feasibility during the construction process. Extensive experiments demonstrate that the proposed PPM outperforms existing state-of-the-art algorithms in terms of solution quality and timeliness, and the backtracking mechanism effectively improves the scenario completion rate. The model study indicates the efficacy of our training algorithm and the generalisation of the PPNN. Additionally, our construction process is problem-tailored and more suitable for addressing UPEC than iterative search algorithms, because it effectively mitigates the impact of invalid nodes.