Search

Scholarly Works (5 results)

Sort By:

Thesis
Peer Reviewed

Smart Big Data in Precision Agricultural Applications: Acquisition, Advanced Analytics, and Plant Physiology-informed Machine Learning

Niu, Haoyu
Advisor(s): Chen, YangQuan YC

UC Merced Electronic Theses and Dissertations (2022)

Big data acquisition platforms, such as small unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), and proximate sensors for precision agriculture, especially for heterogeneous crops, such as vineyards and orchards, are gaining interest from both researchers and growers. For example, lightweight sensors mounted on UAVs, such as multispectral and thermal infrared cameras, can be used to collect high-resolution images. The higher temporal and spatial resolutions of the images, relatively low operational costs, and nearly real-time image acquisition make the UAVs an ideal platform for mapping and monitoring the variability of crops over large acreage. The data acquisition platforms and analytics can create big data and demand fractional-order thinking due to the “complexity” and, thus, variability inherent in the process. Much hope is placed on machine learning (ML). How can an ML model learn from big data efficiently (optimally) and make the big data “smart” is important in agricultural research? The key to the learning process is the plant physiology and optimization method. Designing an efficient optimization method poses three questions: 1.) What is the best way to optimize? 2.) What is the more optimal way to optimize? 3.) Can we demand “more optimal machine learning,” for example, deep learning with the minimum or smallest labeled data for agriculture? Therefore, in this dissertation, the author investigated the foundations of the plant physiology-informed machine learning (PPIML) and the principle of tail matching (POTM) framework. He elucidated their role in modeling, analyzing, designing, and managing complex systems based on the big data in precision agriculture. Plant physiology entails the complexity of growth. The complex system has both deterministic and stochastic dynamic processes with external driving processes characterized and modeled using fractional calculus-based models, which will better inform the complexity-informed machine learning (CIML) algorithms. Data acquisition platforms, such as low-cost UAVs, UGVs, and edge-AI sensors, were designed and built to demonstrate their reliability and robustness for remote and proximate sensing in agricultural applications. Research results showed that the PPIML, POTM, CIML, and the data acquisition platforms were reliable, robust, and smart tools for precision agricultural research in varying situations, such as water stress detection, early detection of nematodes, yield estimation, and evapotranspiration (ET) estimation. The application of these tools has the potential to assist stakeholders in their crop management decisions.

Cover page: Smart Big Data in Precision Agricultural Applications: Acquisition, Advanced Analytics, and Plant Physiology-informed Machine Learning

Article
Peer Reviewed

Why Do Big Data and Machine Learning Entail the Fractional Dynamics?

UC Merced Previously Published Works (2021)

Fractional-order calculus is about the differentiation and integration of non-integer orders. Fractional calculus (FC) is based on fractional-order thinking (FOT) and has been shown to help us to understand complex systems better, improve the processing of complex signals, enhance the control of complex systems, increase the performance of optimization, and even extend the enabling of the potential for creativity. In this article, the authors discuss the fractional dynamics, FOT and rich fractional stochastic models. First, the use of fractional dynamics in big data analytics for quantifying big data variability stemming from the generation of complex systems is justified. Second, we show why fractional dynamics is needed in machine learning and optimal randomness when asking: "is there a more optimal way to optimize?". Third, an optimal randomness case study for a stochastic configuration network (SCN) machine-learning method with heavy-tailed distributions is discussed. Finally, views on big data and (physics-informed) machine learning with fractional dynamics for future research are presented with concluding remarks.

Creative Commons 'BY' version 4.0 license

Article
Peer Reviewed

Optimal Randomness for Stochastic Configuration Network (SCN) with Heavy-Tailed Distributions

UC Merced Previously Published Works (2021)

Stochastic Configuration Network (SCN) has a powerful capability for regression and classification analysis. Traditionally, it is quite challenging to correctly determine an appropriate architecture for a neural network so that the trained model can achieve excellent performance for both learning and generalization. Compared with the known randomized learning algorithms for single hidden layer feed-forward neural networks, such as Randomized Radial Basis Function (RBF) Networks and Random Vector Functional-link (RVFL), the SCN randomly assigns the input weights and biases of the hidden nodes in a supervisory mechanism. Since the parameters in the hidden layers are randomly generated in uniform distribution, hypothetically, there is optimal randomness. Heavy-tailed distribution has shown optimal randomness in an unknown environment for finding some targets. Therefore, in this research, the authors used heavy-tailed distributions to randomly initialize weights and biases to see if the new SCN models can achieve better performance than the original SCN. Heavy-tailed distributions, such as Lévy distribution, Cauchy distribution, and Weibull distribution, have been used. Since some mixed distributions show heavy-tailed properties, the mixed Gaussian and Laplace distributions were also studied in this research work. Experimental results showed improved performance for SCN with heavy-tailed distributions. For the regression model, SCN-Lévy, SCN-Mixture, SCN-Cauchy, and SCN-Weibull used less hidden nodes to achieve similar performance with SCN. For the classification model, SCN-Mixture, SCN-Lévy, and SCN-Cauchy have higher test accuracy of 91.5%, 91.7% and 92.4%, respectively. Both are higher than the test accuracy of the original SCN.

Cover page: Optimal Randomness for Stochastic Configuration Network (SCN) with Heavy-Tailed Distributions

Article
Peer Reviewed

Evapotranspiration Estimation with Small UAVs in Precision Agriculture

UC Merced Previously Published Works (2020)

Estimating evapotranspiration (ET) has been one of the most critical research areas in agriculture because of water scarcity, the growing population, and climate change. The accurate estimation and mapping of ET are necessary for crop water management. Traditionally, researchers use water balance, soil moisture, weighing lysimeters, or an energy balance approach, such as Bowen ratio or eddy covariance towers to estimate ET. However, these ET methods are point-specific or area-weighted measurements and cannot be extended to a large scale. With the advent of satellite technology, remote sensing images became able to provide spatially distributed measurements. However, the spatial resolution of multispectral satellite images is in the range of meters, tens of meters, or hundreds of meters, which is often not enough for crops with clumped canopy structures, such as trees and vines. Unmanned aerial vehicles (UAVs) can mitigate these spatial and temporal limitations. Lightweight cameras and sensors can be mounted on the UAVs and take high-resolution images. Unlike satellite imagery, the spatial resolution of the UAV images can be at the centimeter-level. UAVs can also fly on-demand, which provides high temporal imagery. In this study, the authors examined different UAV-based approaches of ET estimation at first. Models and algorithms, such as mapping evapotranspiration at high resolution with internalized calibration (METRIC), the two-source energy balance (TSEB) model, and machine learning (ML) are analyzed and discussed herein. Second, challenges and opportunities for UAVs in ET estimation are also discussed, such as uncooled thermal camera calibration, UAV image collection, and image processing. Then, the authors share views on ET estimation with UAVs for future research and draw conclusive remarks.

Cover page: Evapotranspiration Estimation with Small UAVs in Precision Agriculture

Article
Peer Reviewed

The genome sequences of the marine diatom Epithemia pelagica strain UHM3201 (Schvarcz, Stancheva & Steward, 2022) and its nitrogen-fixing, endosymbiotic cyanobacterium.

UC Santa Cruz Previously Published Works (2024)

We present the genome assembly of the pennate diatom Epithemia pelagica strain UHM3201 (Ochrophyta; Bacillariophyceae; Rhopalodiales; Rhopalodiaceae) and that of its cyanobacterial endosymbiont (Chroococcales: Aphanothecaceae). The genome sequence of the diatom is 60.3 megabases in span, and the cyanobacterial genome has a length of 2.48 megabases. Most of the diatom nuclear genome assembly is scaffolded into 15 chromosomal pseudomolecules. The organelle genomes have also been assembled, with the mitochondrial genome 40.08 kilobases and the plastid genome 130.75 kilobases in length. A number of other prokaryote MAGs were also assembled.

Cover page: The genome sequences of the marine diatom Epithemia pelagica strain UHM3201 (Schvarcz, Stancheva & Steward, 2022) and its nitrogen-fixing, endosymbiotic cyanobacterium.