遇见数据集

Isomorph2026/isomorph-supply-chain-sample

收藏
Hugging Face2026-05-19 更新2026-05-31 收录
官方服务:

资源简介:

# ISOMORPH Sample A single-rollout subset of the ISOMORPH release, intended for users who want to inspect file formats and run loaders before pulling the full dataset. We release multivariate logistics time-series data generated by a digital-twin (DT) simulator of a multi-echelon supply chain with an explicit routing network, with the underlying dynamics formulated as a Markov chain. ## Overview The simulator advances a directed routing graph of factories, intermediate warehouses, and a customer-facing destination forward in discrete time. At each step, random Poisson customer demand arrives at the destination, is served from on-hand stock, and triggers replenishment along the network. The network is a directed graph $G=(\mathcal{N},\mathcal{E})$ with three node roles (factories, warehouses, destination), integer per-edge transit times $\tau_e$, and per-step volume capacities $K_e V_e$; Dijkstra's algorithm routes every shipment. The dynamics form a Markov chain $\xi_{t+1} = \Psi(\xi_t, y_t, L_t)$, where $\Psi$ is a deterministic transition map and $(y_t, L_t)$ are the only random inputs (Poisson customer demand and Gaussian source lead times). The demand intensity is a five-component sum: yearly seasonality, weekly seasonality, AR(1) drift, per-item bursts, and a shared macro shock that lifts every item's intensity simultaneously. The state vector $\xi_t$ records on-hand stock, backlog, outstanding orders, in-transit shipments, and a smoothed demand estimate at every location for every item. The released rollout runs on a 13-node US topology (3 sources, 9 warehouses across 5 tiers, NYC destination). ## Contents | Item | Notes | |------------------|-----------------------------------------------------------| | `manifest.csv` | One row, the baseline `output_item50` rollout | | `output_item50/` | Rollout directory; see File schema below | ## Rollout summary - Family: `baseline` - Catalogue size C = 50 items - Horizon T = 52,560 days - Seed: 2025 - All knobs at simulator defaults; see `manifest.csv` for exact values - Approximate on-disk size: ~1.9 GB ## Manifest schema `manifest.csv` has one row per rollout (just one in this sample) and the following columns: | Column | Meaning | |------------------------|-------------------------------------------------------------| | `rollout` | Rollout name (matches the directory under this variant) | | `family` | One of `baseline`, `mixture`, `uq` | | `scenario` | Scenario label within the family | | `n_items` | Catalogue size C (50 or 200) | | `seed` | RNG seed (2025 here) | | `horizon` | Length T in days (52,560 here) | | `path` | Relative path to the rollout directory inside this variant | | `phi_lo`, `phi_hi` | AR(1) coefficient bounds for the demand process | | `shock_count_scale` | Multiplier on per-day shock count | | `shock_height_scale` | Multiplier on shock magnitude | | `burst_rate_scale` | Multiplier on burst arrival rate | | `burst_height_scale` | Multiplier on burst magnitude | | `containers_scale` | Multiplier on edge container counts (capacity) | | `ss_scale` | Multiplier on safety-stock thresholds | | `leadtime_scale` | Multiplier on edge lead times | Three additional simulator knobs are held fixed and therefore omitted from the manifest: `seasonal_scale = 1.0`, `base_lambda_lo = 80.0`, `base_lambda_hi = 250.0`. The exact values are still recorded in `output_item50/scenario.json`. ## File schema Directory layout: ``` isomorph_sample/ ├── manifest.csv ├── README.md ├── LICENSE └── output_item50/ ├── daily_records.parquet ├── shipments.parquet ├── service_summary.parquet ├── inventory_history.parquet ├── backlog_history.parquet ├── intransit_history.parquet ├── demand_signals.npy ├── demand_signals_cols.txt ├── scenario.json ├── edge_list.parquet ├── edge_utilisation.npy └── edge_saturation.npy ``` `T` is the run horizon (52,560 for the released rollout), `C` is the catalogue size (50), and `E` is the number of edges in the network. | File | Shape / format | Contents | |----------------------------|-------------------------------|----------------------------------------------------------------------| | `daily_records.parquet` | rows: T x C | Per-day, per-item demand and service: `day, item, demand, served_from_stock, new_backlog_today, dest_on_hand_end_before_ship, dest_backlog_end_before_ship` | | `shipments.parquet` | rows: variable | One row per shipment: `day, arrival_day, from, to, item, units, path_nodes, edge_times` | | `service_summary.parquet` | rows: C | Per-item totals: `total_demand, served_from_stock, new_backlog_added, fill_rate_stock_only` | | `inventory_history.parquet`| rows: T | On-hand inventory over time | | `backlog_history.parquet` | rows: T | Backlog over time | | `intransit_history.parquet`| rows: T | In-transit units over time | | `demand_signals.npy` | array: T x C, float | Item-level demand series (same content as the `demand` column of `daily_records.csv`, dense form) | | `demand_signals_cols.txt` | text | Item IDs in column order of `demand_signals.npy` | | `scenario.json` | JSON | Exact CLI knobs used to produce the rollout | | `edge_list.parquet` | rows: E | Edge metadata: `edge_id, from, to, travel_time_days, container_volume, num_containers, cap_per_day` | | `edge_utilisation.npy` | array: T x E, float | Per-edge fractional utilisation | | `edge_saturation.npy` | array: T x E, float | Per-edge fractional saturation (cap-relative throughput) | ## Quick load ```python import pandas as pd import numpy as np manifest = pd.read_csv("manifest.csv") row = manifest.iloc[0] X = np.load(f"{row.path}/demand_signals.npy") # T x C cols = open(f"{row.path}/demand_signals_cols.txt").read().strip().split(",") records = pd.read_parquet(f"{row.path}/daily_records.parquet") ``` ## Next step For the full benchmark (49 rollouts including mixture sweeps and 20 LHS UQ perturbations), see `../isomorph_full/`. ## Licence CC-BY-4.0 (see `LICENSE`).

ISOMORPH Sample is a single-rollout subset of the ISOMORPH release, intended for users who want to inspect file formats and run loaders before pulling the full dataset. It contains multivariate logistics time-series data generated by a digital-twin simulator of a multi-echelon supply chain with an explicit routing network, formulated as a Markov chain. The simulator advances a directed routing graph of factories, warehouses, and a destination in discrete time, with random Poisson customer demand and Gaussian source lead times as random inputs. Demand intensity is a five-component sum: yearly seasonality, weekly seasonality, AR(1) drift, per-item bursts, and a shared macro shock. The state vector records on-hand stock, backlog, outstanding orders, in-transit shipments, and a smoothed demand estimate for every item at every location. The released rollout runs on a 13-node US topology (3 sources, 9 warehouses across 5 tiers, NYC destination), with parameters: family baseline, catalogue size 50 items, horizon 52,560 days, seed 2025, and approximate on-disk size ~1.9 GB.

提供机构:
Isomorph2026
搜集汇总
数据集介绍
Isomorph2026/isomorph-supply-chain-sample 数据集图片
构建方式
置身于多级供应链数字孪生与马尔可夫动态仿真交汇的研究脉络,isomorph-supply-chain-sample 的构建依托 ISOMORPH 发布中的单次 rollout 子集。其仿真器在离散时间上推进由工厂、中间仓库与客户目的地组成的有向路由图,节点角色明确,边具备整数运输时间与逐日容量,配送经 Dijkstra 算法寻路。每步以泊松客户需求抵达目的地并触发补货,随机源仅含泊松需求与高斯源提前期,系统状态由确定性转移映射驱动,形成马尔可夫链。所发布 rollout 采用 13 节点美国拓扑,包含 3 个源、5 层 9 个仓库与 NYC 目的地,基线目录规模 50 物品,时间跨度 52,560 天,随机种子 2025,参数为模拟器默认值。
特点
在物流时间序列分析与供应链运行评估的语境下,该样本展现出多变量、多层级与网络约束交织的特点。其数据覆盖逐日逐物品需求、现货服务、积压、库存、在途、发货记录及服务汇总,并包含需求信号矩阵、边列表、边利用率与饱和度数组等。底层需求强度由年度季节性、周季节性、AR(1) 漂移、逐项突发与共享宏观冲击五分量合成,状态变量记录各地点各物品的现货、积压、未完成订单、在途与平滑需求估计。样本规模约 1.9 GB,单 rollout 结构便于检视文件格式,manifest 与 scenario.json 保留参数配置,CC-BY-4.0 许可提供复用条件。
使用方法
围绕供应链仿真数据的加载、复现与基准建模需求,该数据集提供明确的快速载入接口与文件组织。用户可先读取 manifest.csv 获取 rollout 路径,再以 pandas.read_parquet 载入 daily_records、shipments、service_summary、inventory_history、backlog_history、intransit_history 与 edge_list,并以 numpy.load 读取 demand_signals.npy、edge_utilisation.npy 及 edge_saturation.npy;demand_signals_cols.txt 给出物品列序,scenario.json 记录精确参数。该样本适用于验证数据加载流程、检查 parquet 与 npy 模式、开展需求与库存动态探索,以及在拉取完整 ISOMORPH 基准前进行轻量实验。
背景与挑战
背景概述
面向多层级供应链数字孪生与物流时序建模的研究脉络,isomorph-supply-chain-sample作为ISOMORPH发布的单次rollout子集,定位于在完整基准下载前核验文件格式、加载流程与数据粒度。该样本以显式路由网络上的工厂、仓库与客户目的地为节点,将库存、缺货、在途与需求估计纳入马尔可夫链状态,并以泊松客户需求和高斯源提前期为随机输入,覆盖美国拓扑的十三节点、五十品类与五万两千五百六十日仿真视界。README未披露具体创建时间及主要研究人员或机构,其核心问题在于为多级补货、路径选择、容量约束与需求冲击下的供应链动态提供可复现的时序基准,对库存控制、数字孪生验证与物流机器学习研究具有方法学参考价值。
当前挑战
该数据集所回应的领域难题,在于多层级供应链中需求、补货、运输时延与容量限制耦合后呈现的高维、非平稳与长程依赖特征,传统单节点库存模型难以刻画跨层路由和共享宏观冲击引发的同步波动;泊松到达、周期季节性与突发需求叠加,使服务率、缺货与在途库存的联合预测面临稀疏事件和分布漂移。构建层面的挑战包括:以数字孪生模拟器维持马尔可夫状态转移的一致性,在五万余日长视界与五十品类下控制约1.9GB数据规模;保证边级利用率、饱和度与节点历史记录在Dijkstra路由和容量约束下自洽;并通过manifest、scenario.json与多格式文件实现跨工具可复现加载,同时为完整基准中的混合场景与不确定性量化留出扩展接口。
常用场景
经典使用场景
置身于多级供应链数字孪生与物流时间序列建模的交汇处,该样本的经典用途在于以轻量单次轨迹完成格式审阅、加载器调试与基线复现。研究者可读取manifest.csv、daily_records.parquet、shipments.parquet、demand_signals.npy及边级利用与饱和数组,核验泊松到店需求、AR(1)漂移、季节性与宏观冲击如何经Dijkstra路由网络转化为补货、在途、库存与积压动态。其13节点美国拓扑与50品类目录保留全量发布的结构语义,因而适合作为算法原型、教学演示与全量基准接入前的预检场景。
衍生相关工作
以该样本为锚点向外延展,相关研究谱系多集中于多级供应链仿真基准、概率需求预测、鲁棒库存控制、深度强化学习补货、图神经网络传播建模与不确定性量化。全量ISOMORPH发布的mixture sweeps与LHS UQ扰动为算法评测和压力测试提供多样情景,样本则充当轻量入口,促进加载器、可视化与原型方法迭代。尽管README未逐一列举下游文献,其设计逻辑与文件模式已足以孕育围绕数字孪生、马尔可夫供应链动力学和端到端履约分析的经典工作,并推动可复现基准在运筹与机器学习交叉领域的应用。
数据集最近研究
最新研究方向
在供应链数字孪生与复杂系统智能决策加速融合的背景下,isomorph-supply-chain-sample所代表的多级物流时序基准正成为前沿研究的重要试验场。其显式路由网络、马尔可夫状态转移以及泊松需求、高斯提前期与宏观冲击叠加机制,支撑图神经网络、强化学习和鲁棒优化用于库存—运输联合决策;同时,路径利用率与饱和度的逐日记录为瓶颈识别、韧性评估和不确定性量化提供细粒度证据。完整版本中的混合情景与LHS扰动,则推动可复现的分布外泛化、压力测试与数字孪生校准研究,对供应链风险治理和智能补货基准具有显著意义。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务