Optimal Sampling Interval Research Articles

A proposal of the optimal sampling interval for shock pulse measurement

A proposal of the optimal sampling interval for shock pulse measurement

Deep Learning Method for Improving Rate of Penetration Prediction in Drilling

Summary The urgent global need to reduce CO2 emissions necessitates the development of sustainable power generation sources. Geothermal power emerges as a renewable and dependable energy option, harnessing the Earth’s natural heat sources for electricity generation. Unlike other renewables, geothermal energy offers uninterrupted power, immune to weather conditions. However, its efficiency hinges on technological innovation, particularly in the challenging realm of geothermal drilling. Rate of penetration (ROP) is a crucial drilling performance metric, and this study explores how deep learning models, particularly transformers, can optimize ROP prediction. Leveraging data from Utah Frontier Observatory for Research in Geothermal Energy (FORGE), we analyze the relationship between drilling parameters and ROP. Traditional drilling optimization methods face limitations, as drilling dysfunctions can disrupt the linear relationship between ROP and weight on bit (WOB). We propose a dynamic approach that allows adapting drilling parameters in real time to optimize ROP. Our experiments investigate optimal sampling intervals and forecast horizons for ROP prediction. We find that a 60-second sampling interval maximizes the transformer model’s forecasting accuracy. Additionally, we explore retraining to fine-tune models for specific wells, improving forecasting performance. Our transformer-based ROP forecaster outperforms deep learning models, achieving a low overall 5.22% symmetrical mean average percentage error (SMAPE) over a forecast horizon of 10 minutes. This model offers opportunities for cost-effective drilling optimization, with real-time accuracy, speed, and scalability. Future work will focus on larger data sets and integration with drilling automation systems to further enhance the model’s practicality and effectiveness in the field.

Optimal sampling interval for characterisation of the circadian rhythm of body temperature in homeothermic animals using periodogram and cosinor analysis.

Core body temperature (T c) is a critical aspect of homeostasis in birds and mammals and is increasingly used as a biomarker of the fitness of an animal to its environment. Periodogram and cosinor analysis can be used to estimate the characteristics of the circadian rhythm of T c from data obtained on loggers that have limited memory capacity and battery life. The sampling interval can be manipulated to maximise the recording period, but the impact of sampling interval on the output of periodogram or cosinor analysis is unknown. Some basic guidelines are available from signal analysis theory, but those guidelines have never been tested on T c data. We obtained data at 1-, 5- or 10-min intervals from nine avian or mammalian species, and re-sampled those data to simulate logging at up to 240-min intervals. The period of the rhythm was first analysed using the Lomb-Scargle periodogram, and the mesor, amplitude, acrophase and adjusted coefficient of determination (R 2) from the original and the re-sampled data were obtained using cosinor analysis. Sampling intervals longer than 60 min did not affect the average mesor, amplitude, acrophase or adjusted R 2, but did impact the estimation of the period of the rhythm. In most species, the period was not detectable when intervals longer than 120 min were used. In all individual profiles, a 30-min sampling interval modified the values of the mesor and amplitude by less than 0.1°C, and the adjusted R 2 by less than 0.1. At a 30-min interval, the acrophase was accurate to within 15 min for all species except mice. The adjusted R 2 increased as sampling frequency decreased. In most cases, a 30-min sampling interval provides a reliable estimate of the circadian T c rhythm using periodogram and cosinor analysis. Our findings will help biologists to select sampling intervals to fit their research goals.

Contrast estimation of the Vasicek integrated diffusion process for high-frequency data

The purpose of this paper is to study the parameter estimation of the Vasicek integrated diffusion process. Based on the contrast function, the parameter contrast estimators of the Vasicek integrated diffusion process are given, and the mean-square errors of drift parameter estimators are derived, so as to obtain the optimal sampling intervals for the parameter estimators. Then we prove the strong consistency of the contrast estimators by the tail probability exponential inequality of α-mixing long-span high-frequency data. In numerical simulation, we investigate the fitting effect of the estimates under different sampling intervals and different sample sizes. The results indicate that using optimal interval sampling can achieve good estimation performance. We use the daily closing price data of CSI 300 index to conduct an empirical analysis and give a logarithmic price prediction model. The analysis results show that the prediction model works well.

Determining the optimal sampling interval for 3D morphology measurements of different-sized natural rock joints

Efficiently studying the scale effect of surface roughness and peak shear strength of natural rock joints, especially unfilled and well-matched ones, requires an optimal sampling interval to realize cost-effective three-dimensional morphology measurements for different-sized natural rock joints with advanced non-contact optical devices. However, rationally determining such an optimal sampling interval remains controversial. To this end, inspired by digital signal processing, the optimal sampling interval is creatively determined by Shannon's sampling theorem using the Fourier series' optimum order. An empirical formula relating the joint size to the optimum order is correspondingly developed. The proposed empirical formula was found to work well under conditions of high normal stress, where the relative errors for the surface roughness and peak shear strength of series-sized natural rock joints were mostly less than 10% and 5%, respectively, but should be used cautiously under conditions of low normal stress. Furthermore, different from previous perceptions, a higher joint roughness level was discovered to not necessarily imply the need for a smaller optimal sampling interval, and conversely. The proposed empirical formula can facilitate the determination of the optimal sampling interval for measuring different-sized natural rock joints' surface morphologies in engineering practice.

In situ simultaneous measuring method for the determination of key processes of soil organic carbon cycling: Soil microbial respiration using laser spectrometry.

Soil microbial heterotrophic C-CO2 respiration is important for C cycling. Soil CO2 differentiation and quantification are vital for understanding soil C cycling and CO2 emission mitigation. Presently, soil microbial respiration (SR) quantification models are based on native soil organic matter (SOM) and require consistent monitoring of δ13C and CO2. We present a new apparatus for achieving in situ soil static chamber incubation and simultaneous CO2 and δ13C monitoring by cavity ring-down spectroscopy (CRDS) coupled with a soil culture and gas introduction module (SCGIM) with multi-channel. After a meticulous five-point inter-calibration, the repeatability of CO2 and δ13C values by using CRDS-SCGIM were determined, and compared with those obtained using gas chromatography (GC) and isotope ratio mass spectrometry (IRMS), respectively. We examined the method regarding quantifying SR with various concentrations and enrichment of glucose and then applied it to investigate the responses of SR to the addition of different exogenous organic materials (glucose and rice residues) into paddy soils during a 21-day incubation. The CRDS-SCGIM CO2 and δ13C measurements were conducted with high precision (<1.0µmol/mol and 1‰, respectively). The optimal sampling interval and the amount added were not exceeded 4 h and 200mg C/100g dry soil in a 1 L incubation bottle, respectively; the 13C-enrichment of 3%-7% was appropriate. The total SR rates observed were 0.6-4.2µL/h/g and the exogenous organic materials induced -49%-28% of priming effects in native SOM mineralisation. Our results show that CRDS-SCGIM is a method suitable for the quantification of soil microbial CO2 respiration, requiring less extensive lab resources than GC/IRMS.

Strong consistency of parameter estimation for the CIR integrated diffusion process with long-span high-frequency data

In this article, we utilize the contrast function of the integrated diffusion process to derive parameter contrast estimators for the Cox-Ingersoll-Ross integrated diffusion process and discuss the asymptotic properties of the estimators using the mixing properties of the process. We first give the tail probability exponential inequality of the mixing long-span high-frequency data. Then, applying this inequality, we prove the strong consistency of the contrast estimators for the drift parameters and diffusion parameter of the CIR integrated diffusion process. In order to obtain these asymptotic properties, we require relatively low order r of the negative power moment E | X t − 1 | r of the diffusion process. In the existing literature, r > 9 is required in order to obtain weak consistency of the estimators. However, in our theorems, only r > 2 is required for the strong consistency of the diffusion parameter estimator, while r > 4 for the strong consistency of the drift parameter estimators. In the simulation analysis, we use the Euler discretization algorithm and the Milstein discretization algorithm, and the results show that the optimal sampling interval is around n − 1 / 3 . We use the daily log price data of the CSI 300 Index to estimate the CIR integrated diffusion model and construct a Bootstrap prediction model for the log price. The results show that the model has a good predictive performance.

A line-of-sight zoning method for intervisibility computation by considering terrain relief

Existing intervisibility analysis methods suffer from computational inefficiency due to redundant sampling points. To address this issue, we propose a new approximate method called line-of-sight (LoS) zoning, which leverages continuous terrain relief to identify potentially obscuring zones (POZ) of LoS. By limiting the sampling range to a much smaller POZ, the number of sampling points is significantly reduced. The optimal sampling interval of 6 is determined by striking a balance between computational efficiency and accuracy. Through experiments in both mountainous and plain areas, regardless of the height range and resolution conditions, we demonstrate the high efficiency of the LoS zoning method, especially in scenarios with a high proportion of visible LoS. To account for potential visibility errors caused by sharp peaks in the terrain, we conducted experiments under fixed time intervals to assess the calculation quality of different methods. The results show that in mountainous and plain areas, the improvement in detection rate compared to the hopping strategy method is around 4–6 times in most scenarios. This significant performance enhancement highlights the superiority of the LoS zoning method, and shows great promise in terrain avoidance, path planning in the military, and detection of dangerous targets.

Energy Efficient Sampling Policies for Edge Computing Feedback Systems

We study the problem of finding efficient sampling policies in an edge-based feedback system, where sensor samples are offloaded to a back-end server that processes them and generates feedback to a user. Sampling the system at maximum frequency results in the detection of events of interest with minimum delay but incurs higher energy costs due to the communication and processing of redundant samples. On the other hand, lower sampling frequency results in higher delay in detecting the event, thus increasing the idle energy usage and degrading the quality of experience. We quantify this trade-off as a weighted function between the number of samples and the sampling interval. We solve the minimisation problem for exponential and Rayleigh distributions, for the random time to the event of interest. We prove the convexity of the objective functions by using novel techniques, which can be of independent interest elsewhere. We argue that adding an initial offset to the periodic sampling can further reduce the energy consumption and jointly compute the optimum offset and sampling interval. We apply our framework to two practically relevant applications and show energy savings of up to 36% when compared to an existing periodic scheme.

Validation of a methodology for characterization of rumination, lying, standing, and performing non-nutritive oral behaviors and behavioral patterns in Holstein dairy calves

Calf behavior is closely related to its early growth, production performance, and health performance. Continuous behavior recording is the most accurate but also time-consuming method used for monitoring animal behaviors, so the instantaneous sampling method is often adopted to minimize the time required to quantify behavioral observations in animal studies. Moreover, the optimal sampling intervals required to yield accurate information for estimating Holstein dairy calves' behaviors are still unknown. Our primary objective was to determine the most optimal sampling intervals for monitoring behaviors of Holstein dairy calves during preweaning and weaning periods to improve efficiency while maintaining reliability. The secondary objective was to describe their behavioral patterns. Rumination, lying, standing, and non-nutritive oral behavior (NNOB) data of 18 calves (observation time: 360 h/calf, 6,480 h in total) were continuously recorded for 15 d (3 d at 1, 3, 6, 9, and 12 wk of age). The continuous behavioral data were compared with instantaneous sampling at 5 s, 10 s, 15 s, 30 s,1 min, 3 min, 5 min, 10 min, 15 min, 30 min, and 60 min intervals. Sampling intervals were considered accurate if they met 4 criteria: coefficient of determination ≥0.90 (i.e., strongly related to true values), slope = 1, intercept = 0 (i.e., they did not over- or underestimate true values), and relative error <10%. The most optimal sampling interval was considered the highest sampling interval among the 11 sampling intervals that meet the criteria for accurate monitoring. As expected, the strength of the linear relationship between the continuous recording and instantaneous sampling decreased as the sampling intervals increased. The results varied across the different behaviors, with rumination, lying, standing, and NNOB being reliable at instantaneous recordings of 3 min, 10 min, 10 min, and 1 min for the preweaning period (1, 3, and 6 wk of age) and 10 min, 10 min, 15 min, and 3 min for the postweaning period (9 and 12 wk of age). In terms of behavioral patterns, lying time decreased, whereas rumination, standing, and NNOB time increased with age. After weaning, no significant changes in time spent performing these behaviors. Additionally, the rumination behavioral pattern becomes stable after wk 6 with decreasing after the morning feeding and occurring mainly in the morning. In conclusion, instantaneous sampling is a reliable method for monitoring the behaviors of dairy calves, but the optimal sampling intervals should be selected based on different ages and management conditions.

Morphological classification method and data-driven estimation of the joint roughness coefficient by consideration of two-order asperity

Abstract The roughness of the joint surface plays a significant role in evaluating the shear strength of rock. The waviness (first-order) and unevenness (second-order) of natural joints have different effects on the characterization of joint surface roughness. To accurately quantify the influence of the two-order asperity on the joint roughness coefficient (JRC) prediction of joint surface profile curve, the optimal sampling interval of the asperity was determined through the change of the R p {R}_{{\rm{p}}} value of the joint surface profile curve. The separation of the two-order asperity of 48 joint surface profile curves was completed at the optimal sampling interval, and morphological parameters of the asperity such as i ave {i}_{{\rm{ave}}} , R max {R}_{{\rm{\max }}} , and R p {R}_{{\rm{p}}} were counted from three aspects: asperity angle of the profile curve, asperity degree, and the trace length. Based on the statistical results of the morphological parameters considering the two-order asperity, the new nonlinear prediction models were proposed. The results showed that the curve slope mutation point SI = 2 mm is the optimal separation distance of the two-order asperity of the joint surface profile curve. The refined separation method that considers the waviness and unevenness of morphological parameters can characterize the detailed morphological features of the joint surface in more dimensions. The support vector regression (SVR) and random forest (RF) models that take into account a two-order asperity separated results have higher accuracy than traditional models. The prediction accuracy has improved by 7–8% in SVR model compared with SVR(SO) and RF(SO). The SVR nonlinear model that considering separation of two-orders of joint surface roughness is more suitable for the prediction of JRC.

Feature engineering process on well log data for machine learning-based SAGD performance prediction

The conventional numerical simulation requires a reliable three-dimensional reservoir model to evaluate the steam-assisted gravity drainage (SAGD) performance, but it may be time-consuming and need a significant amount of static data. This study aims to develop a machine learning (ML) model that predicts the SAGD performance based on well log data from a near single well. Although the ML model is useful in capturing underlying non-linear relationships between input features and target features, it requires a large number of training data. However, the number of data is usually small in commercial fields, limiting the availability of all log responses as input features to consider reservoir heterogeneity. In case of using small dataset, the overfitting can occur with an excessive number of model parameters. Therefore, this study introduces a feature engineering process to extract and select key features from well log data to alleviate the overfitting problem.In this study, the feature engineering process was optimized by sensitivity analysis on feature extraction and feature selection methods. For data preparation, the 63 SAGD well pairs and their matched logged wells were screened from the six commercial oil sand fields in Alberta, Canada. The SAGD process mechanism and petrophysics were considered to build data screening criteria. Each depth of the log data was categorized into pay-zone or shale barrier. For feature extraction, sampling intervals were placed on log data. This calculates the net pay thickness, averaged gamma ray, deep resistivity, and neutron porosity logs in the pay-zone. In addition, the elevation of two shale barriers and the distance between the SAGD well and logged well are extracted. Sensitivity analysis of the sampling interval length was conducted to determine the optimal conditions considering heterogeneity and feature reduction. For the feature selection, various combinations of the extracted features were used to examine their inherent meaning for predicting the SAGD performance. The multi-layer perceptron model was trained based on various selected features to predict the SAGD performance indicators of a seven-year operation. The optimal sampling interval length was determined as 10m and the combination of gamma ray, deep resistivity, shale barrier elevation, and the distance information was selected as key input features. The model showed reasonable prediction results for SAGD productivity and economic indicator with R2 of 0.67 and 0.72, respectively.

Detecting peatland vegetation patterns with multi-temporal field spectroscopy

ABSTRACT Peatlands are one of the most significant terrestrial carbon pools, and the processes behind the carbon cycle in peatlands are strongly associated with different vegetation patterns. Handheld spectroradiometer data has been widely applied in ecological research, but there is a lack of studies on peatlands assessing how the temporal and spectral resolution affect the detectability of vegetation patterns. We collected field spectroscopy and vegetation inventory data at two northern boreal peatlands, Lompolojänkkä and Halssiaapa, between late May and August 2019. We conducted multivariate random forest regressions to examine the appropriate periods, benefits of multi-temporal data, and optimal spectral bandwidth and sampling interval for detecting plant communities and the two-dimensional (2D) %-cover, above-ground biomass (AGB) and leaf area index (LAI) of seven plant functional types (PFTs). In the best cross-site regression models for detecting plant community clusters (PCCs), R2 was 42.6–48.0% (root mean square error (RMSE) 0.153–0.193), and for PFT 2D %-cover 53.9–69.8% (RMSE 8.2–17.6%), AGB 43.1–61.5% (RMSE 86.2–165.5 g/m2) and LAI 46.3–51.3% (RMSE 0.220–0.464 m2/m2). The multi-temporal data of the whole season increased R2 by 13.7–24.6%-points and 10.2–33.0%-points for the PCC and PFT regressions, respectively. There was no single optimal temporal window for vegetation pattern detection for the two sites; in Lompolojänkkä the early growing season between late May and mid-June had the highest regression performance, while in Halssiaapa, the optimal period was during the peak season, from July to early August. In general, the spectral sampling interval between 1 to 10 nm yielded the best regression performance for most of the vegetation characteristics in Lompolojänkkä, whereas the optimal range extended to 20 nm in Halssiaapa. Our findings underscore the importance of fieldwork timing and the use of multi-temporal and hyperspectral data in detecting vegetation in spatially heterogeneous landscapes.

High-Resolution Tap-Based IoT System for Flow Data Collection and Water End-Use Analysis

Knowledge on water-use patterns in residential settings can help policymakers formulate well-targeted water conservation measures and evaluate the efficacy of such measures. Prior studies have applied machine learning techniques to disaggregate household-level water consumption data, collected by smart meters, into specific end-use categories, such as showering, basin use, kitchen use, and use by washing machine. However, the analysis of the effect of the sampling interval on the classification accuracy level remains an underinvestigated issue. This article seeks to fill this knowledge gap by identifying an optimal sampling interval that can achieve a high level of classification accuracy while overcoming constraints of on-device data storage, data transmission, and energy consumption. To understand the benefits of collecting fine-grained data for machine learning, we have built a high-resolution tap-based Internet of Things (IoT) system comprising a set of Wi-Fi-based tap sensors, gateway infrastructure, and a secure data processing pipeline. Based on empirical tap-based data collected over an eight-month period, we concluded that when the sampling interval decreases slightly from 5 to 1 s, the accuracy level of the end-use classification model increases significantly from 66.6% to 76.1 %. This article also highlights the challenges of deploying IoT sensors to collect water consumption data in a domestic setting. In order to collect sufficient ground-truth data for the training and verification of a generalizable water end-use disaggregation model, it is necessary to sophisticate the flow data collection system by adopting low-power wide-area network technologies and reducing the level of energy consumption of the flow sensing components.

Sampling optimization for 3D surface measurement. Part II: Sampling interval optimization based on cumulative power spectral density analysis

Sampling interval is a key sampling parameter in 3D surface measurement, which affects uncertainty and time of measurement. This study aimed to optimize the sampling interval of 3D isotropic and anisotropic surfaces based on cumulative power spectral density (PSD) analysis for the comparability of 3D surface measurement meanwhile ensuring the measurement efficiency. Twenty-four surfaces with expected height distribution and spatial distribution were generated based on Fast Fourier Transform (FFT) and autocorrelation length function. The effects of sampling interval on surface texture parameters and cumulative PSD of isotropic and anisotropic surfaces were investigated under the conditions of redundant, appropriate and distorted sampling intervals, respectively. The results show 3D texture parameters were insensitive to sampling interval, but cumulative PSD significantly depends on sampling interval. Therefore, based on the cumulative PSD analysis, the optimal sampling intervals for isotropic and anisotropic surfaces with different mean surface height ranges were given. It also indicates that the optimal sampling intervals parallel to the texture direction were higher 10–20 times than that perpendicular to texture direction for anisotropic surfaces. In addition, to verify the validity of the recommended sampling intervals, three actual surfaces were machined using different abrasive grit burs and were measured using a non-contact confocal profiler with the optimal sampling intervals recommended. They demonstrate that the recommended optimal sampling intervals could be used as the sampling parameter selection guidance for 3D surface measurement and characterization.

Economic-Statistical Performance of Auxiliary Information-Based Maximum EWMA Charts for Monitoring Manufacturing Processes

An auxiliary information-based maximum exponentially weighted moving average chart, namely, the AIB-MaxEWMA chart, is superior to the existing MaxEWMA chart in detecting small process mean and/or variability shifts. To date, AIB-MaxEWMA chart was designed based on the statistical perspective, which ignores the cost of process monitoring. The economic-statistical performance of the AIB-MaxEWMA chart for monitoring process shifts is investigated. The Monte Carlo simulation was conducted to determine the optimal decision variables, such as sample size, sampling interval, control limit constant, and smoothing constant, by minimizing the expected cost function under the statistical constraints. Numerical simulations indicate that when an auxiliary variable is highly related to the study variable, AIB-MaxEWMA charts not only have better statistical performance, but also have lower expected costs than MaxEWMA charts. Sensitivity analyses also show that a larger expected time to sample an auxiliary variable results in larger optimal expected costs and lower optimal sample size and sampling interval. The relationship between optimal decision variables and minimal costs is valuable for reference by researchers or process engineers.

Joint Optimization of Control Strategy and Energy Consumption for Energy Harvesting WSAN.

With the rapid development of wireless sensor technology, recent progress in wireless sensor and actuator networks (WSANs) with energy harvesting provide the possibility for various real-time applications. Meanwhile, extensive research activities are carried out in the fields of efficient energy allocation and control strategy design. However, the joint design considering physical plant control, energy harvesting, and consumption is rarely concerned in existing works. In this paper, in order to enhance system control stability and promote quality of service for the WSAN energy efficiency, a novel three-step joint optimization algorithm is proposed through control strategy and energy management analysis. First, the optimal sampling interval can be obtained based on energy harvesting, consumption, and remaining conditions. Then, the control gain for each sampling interval is derived by using a backward iteration. Finally, the optimal control strategy is determined as a linear function of the current plant states and previous control strategies. The application of UAV formation flight system demonstrates that better system performance and control stability can be achieved by the proposed joint optimization design for all poor, sufficient, and general energy harvesting scenarios.

Safety Monitoring System of CAVs Considering the Trade-Off between Sampling Interval and Data Reliability.

The safety of urban transportation systems is considered a public health issue worldwide, and many researchers have contributed to improving it. Connected automated vehicles (CAVs) and cooperative intelligent transportation systems (C-ITSs) are considered solutions to ensure the safety of urban transportation systems using various sensors and communication devices. However, realizing a data flow framework, including data collection, data transmission, and data processing, in South Korea is challenging, as CAVs produce a massive amount of data every minute, which cannot be transmitted via existing communication networks. Thus, raw data must be sampled and transmitted to the server for further processing. The data acquired must be highly accurate to ensure the safety of the different agents in C-ITS. On the other hand, raw data must be reduced through sampling to ensure transmission using existing communication systems. Thus, in this study, C-ITS architecture and data flow are designed, including messages and protocols for the safety monitoring system of CAVs, and the optimal sampling interval determined for data transmission while considering the trade-off between communication efficiency and accuracy of the safety performance indicators. Three safety performance indicators were introduced: severe deceleration, lateral position variance, and inverse time to collision. A field test was conducted to collect data from various sensors installed in the CAV, determining the optimal sampling interval. In addition, the Kolmogorov–Smirnov test was conducted to ensure statistical consistency between the sampled and raw datasets. The effects of the sampling interval on message delay, data accuracy, and communication efficiency in terms of the data compression ratio were analyzed. Consequently, a sampling interval of 0.2 s is recommended for optimizing the system’s overall efficiency.

Urban Catchment-Scale Blue-Green-Gray Infrastructure Classification with Unmanned Aerial Vehicle Images and Machine Learning Algorithms

Green infrastructure (GI), such as green roofs, is now widely used in sustainable urban development. An accurate mapping of GI is important to provide surface parameterization for model development. However, the accuracy and precision of mapping GI is still a challenge in identifying GI at the small catchment scale. We proposed a framework for blue-green-gray infrastructure classification using machine learning algorithms and unmanned aerial vehicle (UAV) images that contained digital surface model (DSM) information. We used the campus of the Southern University of Science and Technology in Shenzhen, China, as a study case for our classification method. The UAV was a DJI Phantom 4 Multispectral, which measures the blue, green, red, red-edge, and near-infrared bands and DSM information. Six machine learning algorithms, i.e., fuzzy classifier, k-nearest neighbor classifier, Bayes classifier, classification and regression tree, support vector machine (SVM), and random forest (RF), were used to classify blue (including water), green (including green roofs, grass, trees (shrubs), bare land), and gray (including buildings, roads) infrastructure. The highest kappa coefficient was observed for RF and the lowest was observed for SVM, with coefficients of 0.807 and 0.381, respectively. We optimized the sampling method based on a chessboard grid and got the optimal sampling interval of 11.6 m to increase the classification efficiency. We also analyzed the effects of weather conditions, seasons, and different image layers, and found that images in overcast days or winter days could improve the classification accuracy. In particular, the DSM layer was crucial for distinguishing green roofs and grass, and buildings and roads. Our study demonstrates the feasibility of using UAV images in urban blue-green-gray infrastructure classification, and our infrastructure classification framework based on machine learning algorithms is effective. Our results could provide the basis for the future urban stormwater management model development and aid sustainable urban planning.

Delineating soil nutrient management zones based on optimal sampling interval in medium- and small-scale intensive farming systems

Delineating soil nutrient management zones based on optimal sampling interval in medium- and small-scale intensive farming systems