About

Yuxin Miao is a Professor and the Director of the Precision Agriculture Center at the Department of Soil, Water, and Climate at the University of Minnesota Twin Cities. His educational background includes a PhD from the University of Minnesota, obtained in 2005. His research group focuses on developing integrated precision agricultural management systems aimed at enhancing food security and sustainable development. He employs a combination of field measurements, active canopy sensors, UAV and satellite remote sensing, crop growth modeling, and other innovative technologies to improve agricultural resource management and environmental protection. Yuxin Miao's work emphasizes the application of remote sensing and sensor technologies to optimize nitrogen use efficiency, diagnose crop nutrient status, and close yield gaps in various cropping systems. His contributions include developing strategies for precision nitrogen management, evaluating sensor systems for crop monitoring, and advancing sustainable agricultural practices through technological innovation. His research aims to provide solutions that support sustainable agriculture and resource conservation.

Research topics

• Machine Learning
• Computer Science
• Biology
• Environmental science
• Mathematics
• Remote sensing
• Artificial Intelligence
• Agronomy
• Engineering
• Agricultural engineering
• Ecology
• Geography
• Statistics

Selected publications

• Long-Term Snow Cover Change in the Qilian Mountains (1986–2024): A High-Resolution Landsat-Based Analysis

  Remote Sensing · 2025-07-18 · 3 citations

  articleOpen access

  Snow cover, as a critical component of the cryosphere, serves as a vital water resource for arid regions in Northwest China. The Qilian Mountains (QLM), situated on the northeastern margin of the Tibetan Plateau, function as an important ecological barrier and water conservation area in western China. This study presents the first high-resolution historical snow cover product developed specifically for the QLM, utilizing a multi-level snow classification algorithm tailored to the complex topography of the region. By employing Landsat satellite data from 1986–2024, we constructed a comprehensive 39-year snow cover dataset at a resolution of 30 m. A dual adaptive cloud masking strategy and spatial interpolation techniques were employed to effectively address cloud contamination and data gaps prevalent in mountainous regions. The spatiotemporal characteristics and driving mechanisms of snow cover changes in the QLM were systematically analyzed using Sen–Theil trend analysis and Mann–Kendall tests. The results reveal the following: (1) The mean annual snow cover extent in the QLM was 15.73% during 1986–2024, exhibiting a slight declining trend (−0.046% yr−1), though statistically insignificant (p = 0.215); (2) The snowline showed significant upward migration, with mean elevation and minimum elevation rising at rates of 3.98 m yr−1 and 2.81 m yr−1, respectively; (3) Elevation-dependent variations were observed, with significant snow cover decline in high-altitude (>5000 m) and low-altitude (2000–3500 m) regions, while mid-altitude areas remained relatively stable; (4) Comparison with MODIS data demonstrated good correlation (r = 0.828) but revealed systematic differences (RMSE = 12.88%), with MODIS showing underestimation in mountainous environments (Bias: −8.06%). This study elucidates the complex response mechanisms of the QLM snow system under global warming, providing scientific evidence for regional water resource management and climate change adaptation strategies.

  PublisherOA PDFDOI

• Evaluating the Potential of Improving In-Season Potato Nitrogen Status Diagnosis using Leaf Fluorescence Sensor as Compared with the SPAD Meter

  Preprints.org · 2025-05-20 · 1 citations

  preprintOpen access

  In-season nitrogen (N) status diagnosis is an effective way to guide split N applications for improved profitability and minimized negative environmental impacts. Petiole nitrate-N concentration (PNNC) has been an industry standard indicator for in-season potato (Solanum tuberosum L.) N status diagnosis but is limited because of destructive sampling and chemical processing needs. Leaf sensors can be used to predict PNNC and other N status indicators and overcome these challenges. The SPAD meter is a sensor commonly used to estimate leaf chlorophyll (Chl) based on transmittance, while Dualex is a newer leaf sensor that can also measure leaf flavanol (Flav) and anthocyanin (Anth) through Chl fluorescence. Limited research has been conducted to compare the two leaf sensors for potato N status assessment, despite their respective success in N status diagnosis for other crops. Therefore, the objectives of this study were to 1) compare the performance of the Dualex sensor relative to the SPAD meter for predicting potato N status indicators when only sensor data are used, 2) evaluate the potential of improving potato N status prediction using multi-source data fusion compared with only using leaf sensor data, and 3) develop practical strategies for leaf-sensor-based in-season potato N status diagnosis. The plot-scale experiments were conducted in Becker, Minnesota, USA in 2018, 2019, 2021, and 2023 involving different cultivars, N treatments, and irrigation treatments in a split plot design with three replications. Leaf sensor data and plant samples were simultaneously collected and processed multiple times at key growth stages each year. Daily weather data were also collected at the on-site weather station. Different in-season potato N status indicators including PNNC and N nutrition index (NNI) were derived from plant samples, while weather- and management-related parameters were calculated using the weather data and management records. Dualex’s N balance index (NBI; Chl/Flav) always outperformed Dualex Chl but did not consistently perform better than the SPAD meter. All N status indicators were predicted with significantly higher accuracy with multi-source data fusion using machine learning models. A practical in-season potato N status diagnostic strategy was developed using linear support vector regression model with SPAD, cultivar information, accumulated growing degree days (GDDs), accumulated total moisture, and as-applied N rate to predict vine or whole plant NNI, achieving an R² of 0.80 - 0.82, accuracy of 0.75 - 0.77, and a Kappa statistic of 0.57 - 0.58 (near-substantial). Further research is also required to determine the critical N dilution curve and sufficiency ranges of NNI for potatoes based on different genetic, environmental, and management conditions to better support decision-making.

  PublisherOA PDFDOI

• Optimizing on-farm corn yield prediction by a multi-source data fusion approach using remote sensing and machine learning

  Smart Agricultural Technology · 2025-11-17 · 4 citations

  articleOpen accessCorresponding

  • Multi-source data fusion improved on-farm corn yield prediction accuracy • August 10–31 identified as optimal window for yield estimation using VIs • Random forest outperformed seven other ML models with R² > 87% • Sentinel-2 and Landsat 8 both effectively supported corn yield prediction • Adding topographic and soil variables significantly reduced MAE vs. VIs alone Corn ( Zea mays L. ) is a cornerstone crop for global food security, providing nearly 30% of daily calories to over 4.5 billion people. Therefore, it is crucial to maximize corn yield by optimizing corn production management, for which accurate and timely corn yield prediction is essential. Remote sensing data integrated with machine learning (ML) models have been widely used for corn yield prediction. However, several research gaps remain, including the identification of the optimal time window during which vegetation indices (VIs) most effectively contribute to yield estimation; a comparison of the predictive performance of various ML algorithms; the potential enhancements provided by multi-source data fusion; and the relative effectiveness of satellite platforms such as Sentinel-2 (S2) and Landsat 8 (L8) imagery. To address these gaps, a study was conducted on three rainfed corn fields in Minnesota, USA, using observed yield monitor data. Multiple VIs derived from imagery of S2 and L8 satellites characterizing plant health, biomass, and growth status were used along with POLARIS soil property data and topographic variables extracted from LiDAR-derived digital elevation models. Eight ML algorithms (random forest, decision trees, extra trees, gradient boosting, extreme gradient boosting, K-nearest neighbors, support vector machine, and histogram-based gradient boosting) were evaluated. The results showed that the random forest model consistently outperformed other algorithms, achieving R² values greater than 75% when VIs alone from S2 and L8 imagery were used during the optimal yield prediction window (August 10–31), which aligns with the R4 (Dough) to R5 (Dent) corn growth stages. Multi-source data fusion, specifically the integration of topographic features and POLARIS soil variables with VIs significantly improved prediction accuracy, reducing the mean absolute error by over 40% compared to using VIs alone. Although S2 data offered slight advantages over L8 due to its finer spatial and spectral resolution, L8 also delivered viable results when used with a multi-source data fusion approach, particularly benefiting from its higher radiometric resolution. This study highlights that integrating multiple VIs, soil, and topographic data with ensemble ML models provides a robust, scalable, and operational framework for corn yield prediction. Such approach offers a promising pathway to enhance precision agriculture for more sustainable food systems.

  PublisherDOI

• Research on Cloud-native Framework for Resource-constrained Environments

  2025-10-18

  article

  This research meets the requirements of flexibility, adaptability, agile operation and maintenance, and destruction-resistant replacement in tactical information service environments (e.g., mobile command posts at the tactical edge). Based on the characteristics of "high mobility, weak connectivity, strong confrontation, and multi-platform" of tactical edge environment and the concept of commercial cloud-native technology, a fully peer-to-peer and highly-available cloud-native framework for tactical edge environments is proposed, aiming to improve the rapid setup, agile integration, survivability, and adaptability of tactical information service systems, such as mobile command posts. Overall, this research will shorten the deployment cycle and reduce the operational cost. Maintenance difficulties and maintenance costs of tactical information systems.

  PublisherDOI

• Precipitation influences pre‐sidedress soil nitrate thresholds for corn production

  Soil Science Society of America Journal · 2025-05-01

  articleOpen access

  Abstract Minnesota is a leading corn ( Zea mays L.) producer in the United States, requiring substantial nitrogen (N) inputs for optimal yields. Using an in‐season critical soil nitrate (NO 3 − ‐N) concentration threshold to adjust fertilization rates can improve N management and reduce environmental impacts. This study assessed corn grain yield response to in‐season (i.e., V4–V6 corn development stage) soil NO 3 − ‐N concentration to establish a critical pre‐sidedress soil NO 3 − ‐N test (PSNT) under Minnesota conditions. Data included were obtained from 34 field experiments conducted from 2012 to 2019 across the major corn production regions of Minnesota. Relationships between PSNT and relative corn grain yield were analyzed using a quadratic‐plateau regression model. Across the entire dataset, a PSNT of 20 ± 2.5 mg NO 3 − ‐N kg −1 soil was the critical level to reach 97% of maximum corn grain yield. To increase suboptimum PSNT concentrations up to the critical threshold, application of 13.8 ± 2.4 kg N ha −1 is needed per 1 mg kg −1 increase in soil NO 3 − ‐N concentration based on pre‐/at planting N application, but validation is needed for actual sidedress applications. When precipitation was lower or greater than the 30‐year mean, the critical PSNT value was 21.5 or 17.4 mg kg⁻¹, respectively. Nonetheless, the 20 ± 2.5 mg NO 3 − ‐N kg −1 PSNT critical value is applicable across the state as limited model improvements were achieved when the data were segregated according to soil characteristics, location, corn material, and/or previous crop.

  PublisherOA PDFDOI

• In-season prediction of corn yield and economic optimum nitrogen rate using stacking regression

  2025-06-18

  book-chapterOpen access

  The objectives of this study were to (1) evaluate different machine learning (ML) models for inseason prediction of corn (Zea mays L.) yield, and (2) develop a-ML-based strategy for in-season site-specific economic optimum N rate (EONR) estimation across the US Corn Belt. Forty-nine site-years of N rate experiments were used. Results indicated that stacking regression (STR) had the best performance in both grain yield (R2≥0.80 and EONR estimation (R2=0.89). It is concluded that multi-source data fusion using stacking regression is a promising strategy to predict corn yield and EONR for in-season N management across the US Corn Belt.

  PublisherOA PDFDOI

• Potential of Multi-Source Multispectral vs. Hyperspectral Remote Sensing for Winter Wheat Nitrogen Monitoring

  Remote Sensing · 2025-08-01 · 3 citations

  articleOpen access

  Timely and accurate monitoring of crop nitrogen (N) status is essential for precision agriculture. UAV-based hyperspectral remote sensing offers high-resolution data for estimating plant nitrogen concentration (PNC), but its cost and complexity limit large-scale application. This study compares the performance of UAV hyperspectral data (S185 sensor) with simulated multispectral data from DJI Phantom 4 Multispectral (P4M), PlanetScope (PS), and Sentinel-2A (S2) in estimating winter wheat PNC. Spectral data were collected across six growth stages over two seasons and resampled to match the spectral characteristics of the three multispectral sensors. Three variable selection strategies (one-dimensional (1D) spectral reflectance, optimized two-dimensional (2D), and three-dimensional (3D) spectral indices) were combined with Random Forest Regression (RFR), Support Vector Machine Regression (SVMR), and Partial Least Squares Regression (PLSR) to build PNC prediction models. Results showed that, while hyperspectral data yielded slightly higher accuracy, optimized multispectral indices, particularly from PS and S2, achieved comparable performance. Among models, SVM and RFR showed consistent effectiveness across strategies. These findings highlight the potential of low-cost multispectral platforms for practical crop N monitoring. Future work should validate these models using real satellite imagery and explore multi-source data fusion with advanced learning algorithms.

  PublisherOA PDFDOI

• Hydrogen sulfide improves vascular endothelial function in hypertensive states through SIRT6 anti-inflammatory signaling

  Acta Biochimica et Biophysica Sinica · 2025-11-01

  articleOpen access

  Hypertension is commonly accompanied by endothelial dysfunction, characterized by an imbalance between vasodilatation and constriction, increased levels of the proinflammatory factors interleukin-6 (IL-6) and intercellular adhesion molecule-1 (ICAM-1), and decreased nitric oxide (NO) bioavailability. Using an angiotensin II (Ang II)-induced endothelial dysfunction model, we show that treatment with the hydrogen sulfide (H₂S) donor GYY4137 significantly reverses Ang II-induced damage. GYY4137 restores sirtuin 6 (SIRT6) expression, suppresses inflammation, and improves vasodilatory function. Furthermore, endothelial-specific cystathionine-γ-lyase (CSE)-deficient mice exhibit inflammation and endothelial dysfunction in blood vessels, which is reversed by H₂S supplementation. Critically, SIRT6 inhibitors block the protective effects of H₂S in the endothelium. This study demonstrates that H₂S protects vascular endothelial function by activating the SIRT6 anti-inflammatory pathway.

  PublisherOA PDFDOI

• Phosphorus placement and microbial inoculation effects on potato yield and phosphorus recovery

  Agronomy Journal · 2025-05-01

  articleOpen access

  Abstract Potatoes ( Solanum tuberosum L.) have been shown in previous studies to respond to P fertilizer on high‐P testing soils. Response to P under these conditions may be due in part to their shallow root systems and poor associations with mycorrhizal fungi due to the use of fumigation to control soilborne diseases. This study evaluated the effects of P placement and microbial inoculation on tuber yield and P recovery in high‐P soil. A field study with a split–split‐plot randomized complete block design was conducted over 2 years, with whole plots defined by fumigation treatment (no fumigant or metam sodium) and subplots defined by cultivar (Ivory Russet or Russet Burbank). Each subplot was divided into seven sub‐subplots by P treatment. Four treatments were used to evaluate banded versus broadcast P placement at 37 and 73 kg P ha −1 without inoculant. Four treatments were used to evaluate the effect of broadcast P at 0 and 73 kg P ha −1 with or without an inoculant. At equivalent P rates, banded P placement produced 4.8% greater tuber yield, 4.8% greater P uptake, and 5.0% greater P recovery efficiency (PRE) than broadcast placement. However, microbial inoculation had no effect on tuber yield, P uptake, or PRE with or without fumigation. High soil P or control of foliar fungi may have inhibited mycorrhizae. Overall, at equivalent P rates, banded P placement increased tuber yield even under high soil P conditions, but inoculation with arbuscular mycorrhizal fungi and other beneficial microbes had no effect.

  PublisherOA PDFDOI

• Evaluating the Potential of Improving In-Season Potato Nitrogen Status Diagnosis Using Leaf Fluorescence Sensor as Compared with SPAD Meter

  Remote Sensing · 2025-07-05 · 4 citations

  articleOpen accessCorresponding

  The petiole nitrate–nitrogen concentration (PNNC) has been an industry standard indicator for in-season potato (Solanum tuberosum L.) nitrogen (N) status diagnosis. Leaf sensors can be used to predict the PNNC and other N status indicators non-destructively. The SPAD meter is a common leaf chlorophyll (Chl) meter, while the Dualex is a newer leaf fluorescence sensor. Limited research has been conducted to compare the two leaf sensors for potato N status assessment. Therefore, the objectives of this study were to (1) compare SPAD and Dualex for predicting potato N status indicators, and (2) evaluate the potential prediction improvement using multi-source data fusion. The plot-scale experiments were conducted in Becker, Minnesota, USA, in 2018, 2019, 2021, and 2023, involving different cultivars, N treatments, and irrigation rates. The results indicated that Dualex’s N balance index (NBI; Chl/Flav) always outperformed Dualex Chl but did not consistently perform better than the SPAD meter. All N status indicators were predicted with significantly higher accuracy with multi-source data fusion using machine learning models. A practical strategy was developed using a linear support vector regression model with SPAD, cultivar information, accumulated growing degree days, accumulated total moisture, and an as-applied N rate to predict the vine or whole-plant N nutrition index (NNI), achieving an R2 of 0.80–0.82, accuracy of 0.75–0.77, and Kappa statistic of 0.57–0.58 (near-substantial). Further research is needed to develop an easy-to-use application and corresponding in-season N recommendation strategy to facilitate practical on-farm applications.

  PublisherOA PDFDOI

Frequent coauthors

• Georg Bareth

  University of Cologne

  48 shared

• Qiang Cao

  40 shared

• Shanyu Huang

  Ministry of Agriculture and Rural Affairs

  29 shared

• Martin L. Gnyp

  Yara (Germany)

  28 shared

• Junjun Lu

  Women's Hospital, School of Medicine, Zhejiang University

  28 shared

• Xinbing Wang

  Chinese Academy of Agricultural Sciences

  27 shared

• Rui Dong

  26 shared

• Fusuo Zhang

  China Agricultural University

  24 shared

Labs

• Precision Agriculture CenterPI