Hasil untuk "Regional planning"

Argha Ghosh, Arnab Mandal, Bishakha Priyadarshini et al.

Abstract Semi-arid regions are ecologically fragile systems where vegetation dynamics are strongly governed by hydro-meteorological variability. Western Odisha, typifies this climatic sensitivity, with recurrent droughts, erratic rainfall, and high evapotranspiration challenging sustainable land use and agriculture. This study assessed long-term (2001 to 2024) trends of hydro-meteorological and biophysical parameters including precipitation, maximum and minimum air temperature, land surface temperature (LST), actual evapotranspiration (AET), and Normalized Difference Vegetation Index (NDVI) across eight districts of semi-arid Western Odisha using remote sensing datasets and non-parametric trend analysis. Results revealed significant seasonal and spatial heterogeneity. AET exhibited statistically significant declined across most districts during winter and pre-monsoon months, with maximum reductions occurring in April. LST demonstrated widespread cooling during February- May, with rates between − 0.15 and − 0.27 °C year⁻¹ in several districts, while monsoon months showed near-neutral or weakly positive changes. Maximum air temperature displayed strong pre-monsoon warming (0.15–0.22 °C year⁻¹), whereas minimum temperature increased primarily during winter nights (0.05–0.10 °C year⁻¹), indicating intensifying nocturnal warming. NDVI displayed a general greening tendency in pre-monsoon, linked to agricultural intensification, despite declining monsoon precipitation across all districts. LST was highly correlated with maximum air temperature (0.91) and negatively with NDVI (− 0.63). Rainfall exhibited a moderate positive relationship with AET (0.69). The findings highlight a complex climatic transition wherein surface cooling coexists with atmospheric warming, night-time warming, and rainfall reduction. These shifts have direct implications for agricultural water demand, vegetation resilience, and regional climate adaptation planning.

Ali Vaziri, Iman Askari, Huazhen Fang

Robots rely on motion planning to navigate safely and efficiently while performing various tasks. In this paper, we investigate motion planning through Bayesian inference, where motion plans are inferred based on planning objectives and constraints. However, existing Bayesian motion planning methods often struggle to explore low-probability regions of the planning space, where high-quality plans may reside. To address this limitation, we propose the use of heavy-tailed distributions -- specifically, Student's-$t$ distributions -- to enhance probabilistic inferential search for motion plans. We develop a novel sequential single-pass smoothing approach that integrates Student's-$t$ distribution with Monte Carlo sampling. A special case of this approach is ensemble Kalman smoothing, which depends on short-tailed Gaussian distributions. We validate the proposed approach through simulations in autonomous vehicle motion planning, demonstrating its superior performance in planning, sampling efficiency, and constraint satisfaction compared to ensemble Kalman smoothing. While focused on motion planning, this work points to the broader potential of heavy-tailed distributions in enhancing probabilistic decision-making in robotics.

Maya Domeshek, Christoph Graf, Burçin Ünel

Coordinated planning of generation, storage, and transmission more accurately captures the interactions among these three capacity types necessary to meet electricity demand, at least in theory. However, in practice, U.S. system operators typically follow a sequential planning approach: They first determine future generation and storage additions based on an assumed unconstrained (`copper plate') system. Next, they perform dispatch simulations of this projected generation and storage capacity mix on the existing transmission grid to identify transmission constraint violations. These violations indicate the need for transmission upgrades. We describe a multistage, multi-locational planning model that co-optimizes generation, storage, and transmission investments. The model respects reliability constraints as well as state energy and climate policies. We test the two planning approaches using a current stakeholder-informed 20-zone model of the PJM region, developed for the current FERC Order No. 1920 compliance filing process. In our most conservative model specification, we find that the co-optimized approach estimates 67% lower transmission upgrade needs than the sequential model, leading to total system costs that are .6% lower and similar reliability and climate outcomes. Our sensitivities show larger transmission and cost savings and reliability and climate benefits from co-optimized planning.

Jing-Wen Wang, Jing-Wen Wang, Cai-Ting Han et al.

BackgroundThe extensive application of pesticides in agricultural practices is known to affect microbial health and thus eco-multifunctionality in soil. However, previous studies have mainly focused on these effects on whole microbial community in dryland, without considering that in paddy fields under flooded condition, especially lacking the finer insights into subcommunities related to niche fitness.MethodsTo address this issue, the paddy fields, managed with (HP) and without pesticide application (HH) over 8 years, were selected. Then, the occurrence characteristics, function and assembly of generalized and specialized subcommunities classified by niche fitness were investigated.ResultsThe findings revealed that compared to HP model, the microbiota under HH model displayed higher bacterial diversity in both specialists and generalists, as well as greater fungal diversity in the generalists. However, pesticide residues in HP treatment increased copiotrophic microorganisms (e.g., Gemmatimonadota) in paddy soil, whereas oligotrophic microorganisms (e.g., Proteobacteria and Acidobacteriota) were significantly reduced. This indicated a special response of microflora to pesticide application under flooded condition, challenging the traditional views. Despite these changes, HP treatment also exhibited a substantial rise in pathogenic Fusarium, implying a higher diseases risk for rice. Neutral modeling revealed that both bacterial and fungal communities in HP were primarily driven by deterministic processes. Especially for specialists, it had a homogenization selection and diffusional limitation during community succession, because it was characterized by constrained adaptability, narrow ecological niches and high resource specificity. Regarding microbial networks, HP treatment resulted in lower node degree and closeness centrality compared to HH, leading to a decline in the overall functional capacity of the microbial community. FAPROTAX functional predictions further observed a significant reduction in the genes associated with nitrogen cycle and cellulolysis, while the human disease-related genes were increased in HP treatment. Collectively, these findings reveal that pesticide application in paddy fields significantly impacts microbial community structure and function, with specialized subcommunities being particularly vulnerable. These findings broaden our understanding into assembly principles of specialists and generalists under pesticide application in flooded paddy, which will contribute to the sustainable management for rice cultivation.

Alireza Sarsangi Aliabad, Ara Toomanian, Majid Kiavarz et al.

Extended Abstract:1. IntroductionElectricity is an essential input for all production systems and a necessity for all modern families. Hence, relevant energy policies are needed to induce efficient electricity consumption in the residential sector in many countries due to the effects of global warming and security of energy supply. Forecasting electricity demand at a regional or national level is crucial for planning to ensure optimal energy management. Various factors influence household consumption patterns. Factors such as employment rate, residential area, distance from green space, etc. affect electricity consumption. The purpose of this study is to investigate the impact of various factors on electricity consumption in residential homes in Yazd city. The results of this study will be useful for making management decisions for planning to reduce electricity consumption.2. Research MethodologyThe present study was conducted in the city of Yazd, which has a hot and dry climate and is extremely hot in the summer. Data on electricity consumption of Yazd city subscribers was obtained from the provincial electricity distribution company for the years 2016 to 2019. Data related to the city's buildings, such as (current use, building height, area, building shape, and building age), as well as streets, existing street widths, and the location of parks and green spaces, were obtained from the municipality. Spatial configuration indices including: connectivity, depth, coherence and control were estimated. The urban physical parameters of the components of parcel area, building area, yard area, building height, building volume were calculated. Then, association rules were used to examine the existing relationships. Spatial Association Rules are a set of rules that describe the relationships between different features in spatial data. These rules are a capability to find unknown relationships in spatial data. Spatial association rules are rules that indicate the implication of a set of features on another set of features in a spatial database. These rules are introduced to discover the rules between products in large-scale transactional data. 3. Results and discussionResidential electricity consumption data was analyzed using Moran's spatial autocorrelation index and based on Euclidean distance. The results of the study of hot and cold spots of residential electricity consumption data in the study area showed that the distribution of electricity consumption in residential homes is asymmetrical. That is, the number of homes with very high electricity consumption is greater than the number of homes with very low electricity consumption.In total, 3.2 percent of the number of parcels in the region is made up of Low_High outliers and 4.7 percent is High_Low. In the present study, the Apriori algorithm was used. The Apriori algorithm is known as one of the main methods in data mining for discovering association rules. The results of the rule review using Apriori showed that in rule one: buildings with a height of 5 to 8 meters that are located in a new urban context are most likely (93%) to have an annual electricity consumption of more than 3,500 units. Rule two: buildings that are located in a new urban context and their control is less than 1 are most likely (87%) to have an annual electricity consumption of more than 3,500 units. Rule three: buildings that are located in parcels with an area of 150 to 250 square meters and a local connectivity of 2-3 are most likely (74%) to have an annual electricity consumption of more than 3,500 units. Rule four: buildings that are located in parcels with an area of 150 to 250 square meters and in a new urban context and with a yard area of less than 75 square meters are most likely (61%) to have an annual electricity consumption of more than 3,500 units.4. ConclusionAssociation rules are able to extract patterns that cannot be easily identified by traditional methods and provide useful information for optimizing energy consumption.One of the major challenges in using association rules in big data is the need for time-consuming and resource-intensive processing, especially when the data is complex and contains a large number of features. Association rules are usually designed for discrete data, and for numerical data, complex preprocessing such as converting the data to categorical values may be required. Also, the appropriate selection of parameters such as minimum support and confidence can be difficult and have a significant impact on the quality and applicability of the extracted results. It is suggested that in future studies, hourly electricity consumption data should be used if possible so that the effects of more factors can be examined. -

Mharchi Saliha, Mechkirrou Latifa, Slamini Maryam et al.

Unhealthy eating habits are the main cause of the emergence of chronic diseases (CD), especially T2D and hypertension. Previous research confirms that the Mediterranean diet (MD) is one of the most balanced diets available, significantly reducing the risk of CD and improving longevity. Our aim is to identify the components of the MD in an adult population of the eastern region (Berkane and Nador), and to measure the degree of compliance to the MD in this community. A food frequency and MD adherence level analysis questionnaire was used. Our sample comprised 800 consultants, with women for the largest proportion (79%). In fact, 92.5% consumed high-fat products, 75.12% red meats, 56% sweet products, and 43.12% full-fat dairy products. On the other hand, their consumption of beneficial products was below the average indicated. Or, 72.37% of this population have a water intake of less than 1.5L/day, more than a third (38%) don't eat fish, only 43% eat enough cereals and 36% enough fruit and vegetables a day. As a result, the degree of adherence to the Mediterranean diet is characterized by low adherence in more than half 52.37% versus only 47.63% who strongly adhere to the traditional Mediterranean diet. Factors responsible for low adherence were gender p<0.001, residence environment U/R. The study reveals a dietary imbalance in this community, known for its agricultural and maritime wealth. Certain food products are consumed in quantities above or below daily requirements. An overwhelming majority of 47% of the population exhibits a robust compliance with the MD. Furthermore, it was observed that 53% of the subjects studied did not follow this diet, which could be a determining factor in the onset and development of chronic diseases in future generations.

J. Herman, P. Reed, H. Zeff et al.

Yunhao Luo, Chen Sun, Joshua B. Tenenbaum et al.

Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability -- different motion constraints can be easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints.

Victor Hernandez, Iñigo Lara-Aristimuño, Ruben Abella et al.

This study introduces a novel metric, Plan Aperture Modulation (PAM), developed to quantify the modulation of radiotherapy treatment plans. PAM aims to provide a clear geometric interpretation, addressing the limitations of previous complexity metrics and facilitating its integration into treatment planning systems (TPSs) and clinical workflows. The PAM metric was defined as the average fraction of the target area outside the beam aperture, weighted over all control points in a treatment plan. The metric was evaluated in VMAT plans for two sites: prostate with lymph nodes and lung SBRT. Plans with varying complexities were generated using the Eclipse TPS, and PAM was compared to established metrics, including Plan Modulation (PM), Modulation Complexity Score (MCS), and monitor units per Gray (MU/Gy). The relationship between PAM and the Modulation Factor (MF), which quantifies the increase in MUs due to plan modulation, was also investigated. PAM provided a more intuitive assessment of plan modulation compared to the other metrics, and was validated across different delivery systems, such as C-arm linacs and Halcyon systems. The metric outperformed the previous metrics, indicated a zero modulation for Dynamic Conformal Arc plans, and was independent of confounding variables, such as treatment technique, beam energy, delivery system, and patient anatomy. Derived equations enabled the calculation of MF based on PAM, allowing for a robust quantification of plan modulation. PAM is a robust and intuitive metric for quantifying modulation in radiotherapy plans. It overcomes the limitations of previous metrics and can be readily implemented in TPSs to control plan modulation during optimization and for reporting. PAM is a promising tool for improving treatment planning workflows and for comparing and benchmarking radiotherapy plans in multi-institutional studies, clinical trials, and audits.

Sukai Huang, Nir Lipovetzky, Trevor Cohn

Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination. While hybrid LLM-symbolic planning pipelines have emerged as a more robust alternative, they typically require extensive expert intervention to refine and validate generated action schemas. It not only limits scalability but also introduces a potential for biased interpretation, as a single expert's interpretation of ambiguous natural language descriptions might not align with the user's actual intent. To address this, we propose a novel approach that constructs an action schema library to generate multiple candidates, accounting for the diverse possible interpretations of natural language descriptions. We further introduce a semantic validation and ranking module that automatically filter and rank the generated schemas and plans without expert-in-the-loop. The experiments showed our pipeline maintains superiority in planning over the direct LLM planning approach. These findings demonstrate the feasibility of a fully automated end-to-end LLM-symbolic planner that requires no expert intervention, opening up the possibility for a broader audience to engage with AI planning with less prerequisite of domain expertise.

Dillon Z. Chen

Scalable learning for planning research generally involves juggling between different programming languages for handling learning and planning modules effectively. Interpreted languages such as Python are commonly used for learning routines due to their ease of use and the abundance of highly maintained learning libraries they exhibit, while compiled languages such as C++ are used for planning routines due to their optimised resource usage. Motivated by the need for tools for developing scalable learning planners, we introduce WLPlan, a C++ package with Python bindings which implements recent promising work for automatically generating relational features of planning tasks. Such features can be used for any downstream routine, such as learning domain control knowledge or probing and understanding planning tasks. More specifically, WLPlan provides functionality for (1) transforming planning tasks into graphs, and (2) embedding planning graphs into feature vectors via graph kernels. The source code and instructions for the installation and usage of WLPlan are available at tinyurl.com/42kymswc

Mohanraj Devendran Shanthi, Tucker Hermans

Robotic pick and place stands at the heart of autonomous manipulation. When conducted in cluttered or complex environments robots must jointly reason about the selected grasp and desired placement locations to ensure success. While several works have examined this joint pick-and-place problem, none have fully leveraged recent learning-based approaches for multi-fingered grasp planning. We present a modular algorithm for joint pick and place planning that can make use of state of the art grasp classifiers for planning multi-fingered grasps for novel objects from partial view point clouds. We demonstrate our joint pick and place formulation with several costs associated with different placement tasks. Experiments on pick and place tasks with cluttered scenes using a physical robot show that our joint inference method is more successful than a sequential pick then place approach, while also achieving better placement configurations.

Kathryn J. Allen, Danielle C. Verdon-Kidd, Mandy B. Freund et al.

Study region Western Tasmania, southeastern Australia.Study focus We present two new tree-ring based inflow reconstructions from western Tasmania in southeastern Australia.The warm season reconstruction (Dec–Feb) extends from 1030–2007 CE and explains up to 42% of the variance in instrumental flow, while the cool season (JA) extends from 1550–2007 CE and explains 27% of instrumental flow variance. Key features include an extended pluvial period in the 11th Century and a protracted dry period in ∼1500CE, neither of which are represented in the DJF instrumental record. Decreasing JA flow since the 19th Century is consistent with a local sediment-based hydroclimate record.New hydrological insights for the region The reconstructions confirm that the instrumental data do not capture how protracted past low or high flow periods have been. It is therefore important to consider pre-instrumental flow data when planning for the future. The reconstructions provide new insights into regional variability through their association with the Subtropical Ridge (STR) and the Southern Annular Mode (SAM). Differing spatial signatures of the seasonal reconstructions, and their associations with season-specific impacts of STR and SAM, highlight the need for caution when considering the use of remote hydroclimate proxy records with strong seasonal signatures. The reconstructions suggest that extrapolation of seasonally defined reconstructions to represent annual flow for regions beyond the extent of their spatial footprint may be problematic.

Eggy Arya Giofandi, Boedi Tjahjono, Latief Mahir Rachman

Over the past few years, numerous urban areas have been identified in floodplains and coastal regions. These areas should be repurposed as water storage zones to enhance surface water infiltration. The escalating demand for land in flat areas adds complexity to the susceptibility of urban areas to flood hazards. The observation focuses on understanding how land use change influences urban flood susceptibility assessment. Several aspects assumed to have a significant relationship with the flood phenomenon include the impact of land use change, environmental health impact, modification of land typology, explanation of urban flooding, appropriate model for flood-prone assessment, current state of research, appropriate steps in decision-making in susceptibility areas, and challenges of the scenario-based flood-prone mapping model in the future. Additionally, the assessment aspect should consider the impact of land degradation resulting from land use change. Integrated measures are necessary to guide future studies aimed at improving ecological quality and restoring environmental health. The availability of free and open-source datasets facilitates conducting studies to support decision-making both locally and regionally.

Roshan Dhakal, Md Ridwan Hossain Talukder, Gregory J. Stein

We consider a service robot in a household environment given a sequence of high-level tasks one at a time. Most existing task planners, lacking knowledge of what they may be asked to do next, solve each task in isolation and so may unwittingly introduce side effects that make subsequent tasks more costly. In order to reduce the overall cost of completing all tasks, we consider that the robot must anticipate the impact its actions could have on future tasks. Thus, we propose anticipatory planning: an approach in which estimates of the expected future cost, from a graph neural network, augment model-based task planning. Our approach guides the robot towards behaviors that encourage preparation and organization, reducing overall costs in long-lived planning scenarios. We evaluate our method on blockworld environments and show that our approach reduces the overall planning costs by 5% as compared to planning without anticipatory planning. Additionally, if given an opportunity to prepare the environment in advance (a special case of anticipatory planning), our planner improves overall cost by 11%.

Kenny Young, Richard S. Sutton

Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expert Iteration approach to policy learning used in AlphaZero, we propose Option Iteration, an analogous approach to option discovery. Rather than learning a single strong policy that is trained to match the search results everywhere, Option Iteration learns a set of option policies trained such that for each state encountered, at least one policy in the set matches the search results for some horizon into the future. Intuitively, this may be significantly easier as it allows the algorithm to hedge its bets compared to learning a single globally strong policy, which may have complex dependencies on the details of the current state. Having learned such a set of locally strong policies, we can use them to guide the search algorithm resulting in a virtuous cycle where better options lead to better search results which allows for training of better options. We demonstrate experimentally that planning using options learned with Option Iteration leads to a significant benefit in challenging planning environments compared to an analogous planning algorithm operating in the space of primitive actions and learning a single rollout policy with Expert Iteration.

Mohamadreza Ramezani, Hossein Rastgoftar

This paper develops a new approach for robot motion planning and control in obstacle-laden environments that is inspired by fundamentals of fluid mechanics. For motion planning, we propose a novel transformation between motion space, with arbitrary obstacles of random sizes and shapes, and an obstacle-free planning space with geodesically-varying distances and constrained transitions. We then obtain robot desired trajectory by A* searching over a uniform grid distributed over the planning space. We show that implementing the A* search over the planning space can generate shorter paths when compared to the existing A* searching over the motion space. For trajectory tracking, we propose an MPC-based trajectory tracking control, with linear equality and inequality safety constraints, enforcing the safety requirements of planning and control.

Naman Shah, Siddharth Srivastava

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. We present a new approach for bootstrapping the entire hierarchical planning process. This allows us to compute abstract states and actions for new environments automatically using the critical regions predicted by a deep neural network with an auto-generated robot-specific architecture. We show that the learned abstractions can be used with a novel multi-source bi-directional hierarchical robot planning algorithm that is sound and probabilistically complete. An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that (a) our learned abstractions provide the information necessary for efficient multi-source hierarchical planning; and that (b) this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training.

Alan Wilson

Dongchan Kim, Kunsoo Huh

This paper presents a hybrid motion planning strategy that combines a deep generative network with a conventional motion planning method. Existing planning methods such as A* and Hybrid A* are widely used in path planning tasks because of their ability to determine feasible paths even in complex environments; however, they have limitations in terms of efficiency. To overcome these limitations, a path planning algorithm based on a neural network, namely the neural Hybrid A*, is introduced. This paper proposes using a conditional variational autoencoder (CVAE) to guide the search algorithm by exploiting the ability of CVAE to learn information about the planning space given the information of the parking environment. A non-uniform expansion strategy is utilized based on a distribution of feasible trajectories learned in the demonstrations. The proposed method effectively learns the representations of a given state, and shows improvement in terms of algorithm performance.