SEARCH · Search NASA
Results for “decision tree method”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Three-dimensional object recognition using similar triangles and decision trees
A system, TRIDEC, that is capable of distinguishing between a set of objects despite changes in the objects' positions in the input field, their size, or their rotational orientation in 3D space is described. TRIDEC combines very simple yet effective features with the classification capabilities of inductive decision tree methods. The feature vector is a list of all similar triangles defined by connecting all combinations of three pixels in a coarse coded 127 x 127 pixel input field. The classification is accomplished by building a decision tree using the information provided from a limited number of translated, scaled, and rotated samples. Simulation results are presented which show that TRIDEC achieves 94 percent recognition accuracy in the 2D invariant object recognition domain and 98 percent recognition accuracy in the 3D invariant object recognition domain after training on only a small sample of transformed views of the objects.
Case Study: Hybrid Carbon Conversion Using Low-Carbon Energy Sources in Coal-Producing States
The demand for more carbon efficient power sources and a decrease in natural gas prices has decreased the desire for coal power. This decrease in demand has led to massive job losses in coal mining regions over the past decade. The purpose of this project is to develop a hybrid energy system utilizing both a coal power plant and advanced reactor, which is competitive with natural gas by improving on profitability and decreasing carbon emissions. This report details the problem with a summary of the impact on the coal industry and the availability of renewable energy sources in the Appalachian region. Because of the geography of the region, variable renewable energy sources are not available without significant size and siting restrictions. However, biomass in the form of wood waste is abundant and can be used as a carbon neutral energy source. Combining biomass and coal processing, in addition to thermal power plants, can increase system profits and efficiency by providing peaking power and conversion opportunities for secondary markets. The electric load is based on publicly available demand data from Appalachian Power, which services the western Virginia and southern West Virginia in the Appalachian region. The demand information is combined by service, normalized, and scaled to an average demand of 1000 kW, which will be the basis for sizing the hybrid energy system. A traditional screening curve analysis for a coal plant and advanced reactor shows that the least cost design varies significantly based on the assumed discount rate and capital recovery period. An optimization program to size the design in TEAL based on the load curve gives 10 optimal designs, all with a negative resulting net present value (NPV) and a coal plant capacity of less than 15%. Including profits from selling captured carbon at a flat rate results in a positive NPV; however, the coal capacity factor only increases to about 40%. There are limitations with this optimization as well since the price of CO2 is likely to decrease as more is sold to the conversion market. The suggested design will combine coal power, an advanced reactor, and coal and biomass coprocessing to produce a variety of products that can be sold to the conversion market while increasing system efficiency. The analysis of conversion pathways for coal and biomass reveals that multiple options will need to be included in the analysis to produce the optimal system design. Three systems will be optimized and compared to determine the best design based on the figures of merit of total NPV and cost of carbon avoided. The first system will include a coal power plant and an advanced reactor that will sell electricity to the grid to meet demand and sell captured carbon to the conversion market. The second system adds a high-temperature steam electrolysis plant, which will utilize electricity during times of low demand to produce hydrogen and sell it to the conversion market. The third system adds biomass and coal processing with options for hydrocarbon oils, syngas to be produced for the conversion market, and electricity generation to power components within the system or provide peaking power. This analysis will be based on a new approach that combines traditional screening curve methods with a dispatch algorithm that optimizes the system based on the opportunity cost of different production options. The resulting optimization algorithm should provide results with less processing time than HERON’s decision tree method. The results from this analysis will determine an optimal design and reinforce the benefits of coal power when used in a hybrid energy system. The initial results show that the addition of a secondary market for carbon sales could result in a positive NPV and increases the capacity factor of the coal plant as compared to a design with only sales to the electricity market. The addition of more markets and additional coal consumption from biomass coprocessing could increase NPV further, replace carbon in other markets through the sale of biomass-derived hydrocarbons, and demonstrate the value of coal power technology.
A combined machine learning and density functional theory study of binary Ti-Nb and Ti-Zr alloys: Stability and Young’s modulus
The multicomponent Ti alloys, specifically the -phase, have experienced a strong growth over the last decades, due to their outstanding properties of ultra-high strength and low Young’s modulus. These properties play a significant role in many aerospace and biomedical applications. Selection and optimization of multicomponent alloys is challenging due to the vast chemical and compositional space. Here we investigate the use of machine learning techniques informed by density functional calculations to guide the selection of Nb- and Zr-based Ti binary alloys. From the cubic structures obtained from high throughput calculations and literature, we identify several structures with Young’s moduli below 40 GPa. The multivariant decision tree methods provide efficient surrogate models to identify structure variables have high influences on the energetic stability and Young’s modulus. Furthermore, we implement a workflow of incorporating DFT provided results and machine learning method to explore the chemical and composition space of other binary and multicomponent alloys, to eventually accelerate the material design via taking advantages of identified key variables.
Operational Forecasting of Induced Seismicity (CRADA Final Report)
This was a collaborative effort between Lawrence Livermore National Security, LLC ("LLNS"), as manager and operator of Lawrence Livermore National Laboratory ("LLNL"), The Regents of the University of California, as manager and operator of Lawrence Berkeley National Laboratory (Collectively, Contractors) and Nanometrics, Inc. ("Participant"), to develop a toolkit called "Operational Forecasting of Induced Seismicity (ORION)" that includes a decision tree method for operational forecasting of induced seismicity rates related to fluid disposal operations.
Two Trees: Migrating Fault Trees to Decision Trees for Real Time Fault Detection on International Space Station
We started from ISS fault trees example to migrate to decision trees, presented a method to convert fault trees to decision trees. The method shows that the visualizations of root cause of fault are easier and the tree manipulating becomes more programmatic via available decision tree programs. The visualization of decision trees for the diagnostic shows a format of straight forward and easy understands. For ISS real time fault diagnostic, the status of the systems could be shown by mining the signals through the trees and see where it stops at. The other advantage to use decision trees is that the trees can learn the fault patterns and predict the future fault from the historic data. The learning is not only on the static data sets but also can be online, through accumulating the real time data sets, the decision trees can gain and store faults patterns in the trees and recognize them when they come.
Retrofitting Decision Tree Classifiers Using Kernel Density Estimation
A novel method for combining decision trees and kernel density estimators is proposed. Standard.
Paradigms for machine learning
Five paradigms are described for machine learning: connectionist (neural network) methods, genetic algorithms and classifier systems, empirical methods for inducing rules and decision trees, analytic learning methods, and case-based approaches. Some dimensions are considered along with these paradigms vary in their approach to learning, and the basic methods are reviewed that are used within each framework, together with open research issues. It is argued that the similarities among the paradigms are more important than their differences, and that future work should attempt to bridge the existing boundaries. Finally, some recent developments in the field of machine learning are discussed, and their impact on both research and applications is examined.
Performance and calibration of quark/gluon-jet taggers using 140 fb -1 of pp collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector
The identification of jets originating from quarks and gluons, often referred to as quark/gluon tagging, plays an important role in various analyses performed at the Large Hadron Collider, as Standard Model measurements and searches for new particles decaying to quarks often rely on suppressing a large gluon-induced background. This paper describes the measurement of the efficiencies of quark/gluon taggers developed within the ATLAS Collaboration, using $\sqrt{s}$ = 13 TeV proton–proton collision data with an integrated luminosity of 140 fb -1 collected by the ATLAS experiment. Two taggers with high performances in rejecting jets from gluon over jets from quarks are studied: one tagger is based on requirements on the number of inner-detector tracks associated with the jet, and the other combines several jet substructure observables using a boosted decision tree. A method is established to determine the quark/gluon fraction in data, by using quark/gluon-enriched subsamples defined by the jet pseudorapidity. Differences in tagging efficiency between data and simulation are provided for jets with transverse momentum between 500 GeV and 2 TeV and for multiple tagger working points.
Data-driven Cyberattack Detection for Photovoltaic (PV) Systems through Analyzing Micro-PMU Data
With increasing exposure to software-based sensing and control, Photovoltaic (PV) systems are facing higher risks of cyber attacks. Here, to ensure the system stability and minimize potential economic losses, it is imperative to monitor operating states and detect attacks at the early stage. To meet this demand, Micro-Phasor Measurement Units (μPMU) are increasingly popular in monitoring distribution networks. However, due to the relatively low sampling rate, μPMU has not yet been used to detect and classify cyber-attacks in power electronics enabled smart grid. To our knowledge, this is one of the first attempts to use μPMU to detect cyber attacks that degrade the performance of power electronics systems. We propose to apply data-driven methods on micro-PMU data to implement attack detection. We have evaluated data-driven methods, including decision tree (DT), K-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), long short-term memory (LSTM) and convolutional neural network (CNN). The proposed CNN model achieves the required performances with the highest 99.23% accuracy and 0.9963 F 1 score.
Physics-Infused AI/ML Based Digital-Twin Framework for Flow-Induced-Vibration Damage Prediction in a Nuclear Reactor Heat Exchanger
This report summarizes some of the ongoing work related to the development of an expert-elicitation-digital-twin framework for real time damage state prediction in heat exchanger components of a nuclear reactor. The framework is targeted towards predicting damage associated with coupled low cycle fatigue (associated with regular heat-up, cool-down and power operation transients) and high cycle fatigue (associated with flow induced vibration transients). The overall framework will be based on a NoSQL based database, physics-infused-geometry-dependent virtual-sensor data, different AI/ML techniques-based data-driven-predictive-model applications (Apps) and real-time plant sensor measurements available through few existing sensors. Towards this overall goal, this report updates some of the ongoing work, such as on implementation of a NoSQL Database (such as MongoDB), FE based heat transfer analysis of a heat exchanger (e.g. of a PWR steam generator) for generating geometry-dependent virtual sensor data and evaluation of various AI/ML models such as based on multivariate linear regression, ensembled decision-tree based Random-Forest and Gradient-Boosting regression and high-dimensional-kernel-function-transformation based Support-Vector-Machine regression models. The AI/ML models were evaluated for predicting multi-time-series thermal states at thousands of 3D point-clouds
A Machine Learning Approach to Improve Air Traffic Management Initiatives
Collaborating closely with commercial air carriers and related organizations, the Federal Aviation Administration(FAA) regulates air traffic and ensures the safety and efficiency of air operations. Air traffic controllers make strategic decisions, such as delaying, rerouting, or canceling flights, partly based on guidance provided by the FAA’s Air TrafficControl System Command Center (ATCSCC). The guidance includes, among other things, control measures known asTraffic Management Initiatives (TMIs) designed to enhance safety and improve operational efficiency. TMIs play a crucial role in managing the demand and capacity within the U.S. National Airspace System (NAS). Two major TMIs that are routinely used (primarily to mitigate the adverse effects of bad weather) are Ground Delay Programs (GDPs) andGround Stops (GSs). In a GDP, flights destined for airports facing thunderstorm activity experience delays at their origin airports. This proactive approach minimizes the risk of routing aircraft through hazardous weather conditions and also replaces (fuel burning) airborne delays with ground delays. In a GS, a temporary restriction is imposed on the departure or arrival of aircraft at a specific airport or within a designated airspace. Although other TMIs (e.g., miles-in-trail) are also implemented as part of (air) traffic flow management in the NAS, the focus of this work is on GDPs and GSs. Since TMIs, by design, lead to flight delays or cancellations, it is crucial to put in place the right set of parameters(e.g., scope and duration of the GDP). For example, when the end time of a GDP extends beyond what is necessary, it imposes unnecessary delays on departing flights. This situation could occur as a result of inaccurate prediction of the(required) duration of the GDP based on the weather forecast. On the other hand, if a GDP ends prematurely before the underlying capacity constraints are resolved at the destination airport, it may result in airborne holding. The delicate balance lies in matching the termination of the GDP precisely with the resolution of capacity constraints, avoiding both the imposition of unnecessary ground delays and the need for airborne holding due to premature program termination.Failing to specify the right parameters for TMIs also leads to flight delays, creating a significant obstacle in managing the increasing traffic volumes causing increased work load for the controllers. To address this issue, we propose the integration of Machine Learning (ML) models in the traffic flow management(TFM) pipeline. In current operations, decisions are made by human experts based on extensive training, historical patterns, available traffic and weather data. Since we have an abundance of data from past events that tell us the likely impact of various TMIs, by ingesting historical data, properly trained ML models can offer valuable insights and aid human decision-making. With the FAA increasingly exploring advanced analytics, ML emerges as a focal point for enhancing TFM within the National Airspace System (NAS). As a first step, this study aims to provide traffic controllers with decision-making support for the issuance and adjustment of TMIs. Data analytics and machine learning have been previously employed to address some of the challenges associated with TMIs. Numerous studies have concentrated on various facets of TMI issuance, exploring factors influencing TMI parameters, including arrival rate, airport capacity, and delay prediction. For example, using weather forecasts, several statistical methods were used to produce probabilistic capacity profiles which in conjunction with deterministic models provided insights into the GDP planning process [1–4]. The downside of using deterministic models is that they rely on fixed inputs and predetermined rules, which lack the ability to account for the inherent uncertainty and variability present in real-world scenarios. In a separate series of studies, researchers aimed to predict the occurrences of GDPs and GSs. The majority of these studies utilized various supervised learning methods, including Decision Trees, Naive Bayes, Support VectorMachines, and Random Forests to analyze the influence of weather conditions and arrival demand on TMI incidents[5–8]. However, these studies primarily focused on predicting the incidence of TMIs without explicitly addressing the scope of TMIs, including their duration and their geographical coverage. Furthermore, the emphasis of these studies was largely on GDPs, given their higher frequency and longer duration when compared to GSs. A limited number of studies focused on predicting the parameters of TMIs, specifically addressing their duration and extent. In one such study focusing on optimizing the TMI parameters at San Francisco International Airport (SFO),the authors utilized a probabilistic forecast of fog [9]. They simulated various capacity scenarios based on the (fog)burn-off forecasts, selecting GDP parameters that minimized airborne and overall ground delays. However, this approach exclusively emphasizes stratus (fog) burn-off as the primary determinant of GDP and GS, neglecting other influential factors like severe weather events, runway closures, lower capacity than traffic demand, and other important variables. Given the complexity of predicting the TMI and determining its scope, we seek a more holistic approach. We aim to consider all significant factors that could impact TMIs and their parameters. What sets this research apart is the fusion of all data sources relevant to the issuance and adjustment of TMIs and it represents the first comprehensive attempt to optimize TMIs in this manner. Since this comprehensive solution involves various aspects, we break down the problem into smaller components and input all parameters into a unified model called the “TMI Adjuster”. Figure 1 shows the overall framework and the list of datasets used in each model. The objective of the TMI Adjuster module is to deliver reliable, consistent and expedited recommendations for the progression, adjustment, and termination of TMIs. The ML solution entails developing a pipeline capable of predicting the necessity of a TMI (e.g., GS or GDP) along with its various parameters. For example, in the case of a GS, this includes the scope of the GS either in terms of distance from the destination airport or based on pre-defined airspace sectors. Here, scope refers to those regions and departing airports that are subject to the GS. In this paper, we concentrate on the issuance of GSs in the three major airports in the New York area — LaGuardia(LGA), John F. Kennedy International (JFK), and Newark Liberty International (EWR). We fuse traffic, weather and other relevant aviation data from years 2017 to 2019 to train and validate the ML models. In particular, we use the following datasets: •Terminal Aerodrome Forecast (TAF): meteorological forecasts specific to each airport, issued four times a day, covering predefined time periods. •TMI data: includes all GSs and GDPs along with their respective parameters. •Aviation System Performance Metrics (ASPM): includes traffic related data such as aircraft delays, arrival, and departure rates. •Notices to Airmen (NOTAMs): utilized to extract runway closure data and manage interdependencies between terminals in close proximity. •Flight cancellation data •Airspace Flow Programs (AFP): includes information on flight airborne holdings caused by TMIs. The data preprocessing entails transforming ASPM, TMI, AFP, NOTAMs, and weather data into an hourly format and consolidating all datasets by merging them based on date and time as the primary key. The TMI Adjuster framework comprises two parallel models: one dedicated to GS and a second model focused on GDP. As previously mentioned, our specific focus is on the GS model as a multi-classification problem. In this framework, each data point of the GS model input summarizes ten hours of data. Specifically, the data loader for the GS model generates the input and output of the model as follows: at a given time step, the input includes the actual traffic, weather, and TMI data from the two-hour window before the time step, alongside the weather forecast and scheduled traffic for the next 8 hours starting from the time step. Based on this information, the output of the GS model for each time interval consists of three dimensions. The first dimension represents a binary decision on whether there should be a GS in place for the next hour or not. The second dimension is related to the scope of the GS in the United States, and the third dimension is related to the scope of the GS in Canada (i.e., to determine if the GS impacts airports in Canada).One of the challenges with TMI modeling is the sparsity of TMI events, particularly regarding its scope. To address this challenge in the scope of the GS model output, we implement grouping. The GS scope for the US region is defined based on a list of centers that should be included when the GS is in place. With 20 centers in the US, we utilized historical data to group them into 4 categories. In particular, we summarized our historical data in a graph format where nodes represent centers, and link weights are defined based on the co-occurrence of centers in the scope parameter ofTMIs. By identified strongly connected components in this graph, we were able to partition the centers into four groups. We consider two model structures for the GS Model. Firstly, a hierarchical classification model [10], where the human decision-making for a GS is of hierarchical nature. The decision-maker first decides whether there is a need fora GS, and if the answer is yes, determines the scope. A hierarchical classification model organizes the problem into a class hierarchy, typically a tree or a Directed Acyclic Graph (DAG) structure, and considers the dependency of the decision in the previous step to the next component [10]. Here, we employ the local classifier per level approach, which involves training one multi-class classifier for each level of the class hierarchy. The second structure is the independent structure. In this setting, as the name suggests, we do not consider the dependency of the decisions in the different dimensions of the output of the model. Instead, for each dimension, we train a multi-class classifier independently. Table 1 summarizes GS model statistics for training, validation and testing. The table documents the effect of limiting data to the time steps when there was actually a TMI in place or when a TMI had just terminated. This resulted in a more balanced distribution of the GS class(GS positive class)versus “No GS”(GS negative class), which might help the training process. While JFK and LGA follow very similar distributions, with 40% and 42% GS positive class respectively, EWR has proportionally fewer GS incidents at 28%. Our subsequent phase involves evaluating the performance of both hierarchical structure and independent structure using different state-of-the-art multi-class classifier models such as Random Forest, Decision Trees, K-nearest Neighbors, and Logistic Regression and forecast the duration and scope of the GSs.
Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics
We present a novel application of the machine learning / artificial intelligence method called boosted decision trees to estimate physical quantities on field programmable gate arrays (FPGA). The software package fwXmachina features a new architecture called parallel decision paths that allows for deep decision trees with arbitrary number of input variables. It also features a new optimization scheme to use different numbers of bits for each input variable, which produces optimal physics results and ultraefficient FPGA resource utilization. Problems in high energy physics of proton collisions at the Large Hadron Collider (LHC) are considered. Estimation of missing transverse momentum (E T miss ) at the first level trigger system at the High Luminosity LHC (HL-LHC) experiments, with a simplified detector modeled by Delphes, is used to benchmark and characterize the firmware performance. The firmware implementation with a maximum depth of up to 10 using eight input variables of 16-bit precision gives a latency value of $\mathcal{O}$(10) ns, independent of the clock speed, and $\mathcal{O}$(0.1)% of the available FPGA resources without using digital signal processors.
Improve Data Mining and Knowledge Discovery Through the Use of MatLab
Data mining is widely used to mine business, engineering, and scientific data. Data mining uses pattern based queries, searches, or other analyses of one or more electronic databases/datasets in order to discover or locate a predictive pattern or anomaly indicative of system failure, criminal or terrorist activity, etc. There are various algorithms, techniques and methods used to mine data; including neural networks, genetic algorithms, decision trees, nearest neighbor method, rule induction association analysis, slice and dice, segmentation, and clustering. These algorithms, techniques and methods used to detect patterns in a dataset, have been used in the development of numerous open source and commercially available products and technology for data mining. Data mining is best realized when latent information in a large quantity of data stored is discovered. No one technique solves all data mining problems; challenges are to select algorithms or methods appropriate to strengthen data/text mining and trending within given datasets. In recent years, throughout industry, academia and government agencies, thousands of data systems have been designed and tailored to serve specific engineering and business needs. Many of these systems use databases with relational algebra and structured query language to categorize and retrieve data. In these systems, data analyses are limited and require prior explicit knowledge of metadata and database relations; lacking exploratory data mining and discoveries of latent information. This presentation introduces MatLab(R) (MATrix LABoratory), an engineering and scientific data analyses tool to perform data mining. MatLab was originally intended to perform purely numerical calculations (a glorified calculator). Now, in addition to having hundreds of mathematical functions, it is a programming language with hundreds built in standard functions and numerous available toolboxes. MatLab's ease of data processing, visualization and its enormous availability of built in functionalities and toolboxes make it suitable to perform numerical computations and simulations as well as a data mining tool. Engineers and scientists can take advantage of the readily available functions/toolboxes to gain wider insight in their perspective data mining experiments.
Improve Data Mining and Knowledge Discovery through the use of MatLab
Data mining is widely used to mine business, engineering, and scientific data. Data mining uses pattern based queries, searches, or other analyses of one or more electronic databases/datasets in order to discover or locate a predictive pattern or anomaly indicative of system failure, criminal or terrorist activity, etc. There are various algorithms, techniques and methods used to mine data; including neural networks, genetic algorithms, decision trees, nearest neighbor method, rule induction association analysis, slice and dice, segmentation, and clustering. These algorithms, techniques and methods used to detect patterns in a dataset, have been used in the development of numerous open source and commercially available products and technology for data mining. Data mining is best realized when latent information in a large quantity of data stored is discovered. No one technique solves all data mining problems; challenges are to select algorithms or methods appropriate to strengthen data/text mining and trending within given datasets. In recent years, throughout industry, academia and government agencies, thousands of data systems have been designed and tailored to serve specific engineering and business needs. Many of these systems use databases with relational algebra and structured query language to categorize and retrieve data. In these systems, data analyses are limited and require prior explicit knowledge of metadata and database relations; lacking exploratory data mining and discoveries of latent information. This presentation introduces MatLab(TradeMark)(MATrix LABoratory), an engineering and scientific data analyses tool to perform data mining. MatLab was originally intended to perform purely numerical calculations (a glorified calculator). Now, in addition to having hundreds of mathematical functions, it is a programming language with hundreds built in standard functions and numerous available toolboxes. MatLab's ease of data processing, visualization and its enormous availability of built in functionalities and toolboxes make it suitable to perform numerical computations and simulations as well as a data mining tool. Engineers and scientists can take advantage of the readily available functions/toolboxes to gain wider insight in their perspective data mining experiments.
Learning from examples - Generation and evaluation of decision trees for software resource analysis
A general solution method for the automatic generation of decision (or classification) trees is investigated. The approach is to provide insights through in-depth empirical characterization and evaluation of decision trees for software resource data analysis. The trees identify classes of objects (software modules) that had high development effort. Sixteen software systems ranging from 3,000 to 112,000 source lines were selected for analysis from a NASA production environment. The collection and analysis of 74 attributes (or metrics), for over 4,700 objects, captured information about the development effort, faults, changes, design style, and implementation style. A total of 9,600 decision trees were automatically generated and evaluated. The trees correctly identified 79.3 percent of the software modules that had high development effort or faults, and the trees generated from the best parameter combinations correctly identified 88.4 percent of the modules on the average.
Disentangling error structures of precipitation datasets using decision trees
Characterizing error structures in precipitation products not only facilitates their proper applications for scientific and practical purposes but also helps improve their retrieval algorithms and processing methods. Despite the fact that multiple precipitation products have been assessed in the literature, factors that affect their error structures remain inadequately addressed. By interpreting 60 binary decision trees, this study disentangles the error characteristics of precipitation products in terms of their spatiotemporal patterns and geographical factors. Three independent precipitation products - two satellite-based and one reanalysis datasets: the Integrated Multi-satellitE Retrievals for GPM (Global Precipitation Measurement) late run (IMERG-L), Soil Moisture to Rain-Advanced SCATterometer (SM2RAIN-ASCAT), and the Modern-Era Retrospective analysis for Research and Applications, Version 2 uncorrected precipitation output (MERRA2-UC), are evaluated across the contiguous United States from 2010 to 2019. Here, the ground-based Stage IV precipitation dataset is used as the ground truth. Results indicate that the MERRA2-UC outperforms the IMERG-L and SM2RAIN-ASCAT with higher accuracy and more stable interannual patterns for the analysis period. Decision trees cross-assess three spatiotemporal factors and find that the underestimation of MERRA2-UC occurs in the east of the Rocky Mountains, and SM2RAIN-ASCAT underestimates precipitation over high latitudes, especially in winter. Additionally, the decision tree method ascribes system errors to nine different geographical characteristics, of which the distance to the coast, soil type, and DEM are the three dominant features. On the other hand, the land cover type, topography position index, and aspect are three relatively weak factors.