LEADER 05704nam 22006375 450 001 9910842292703321 005 20240305163414.0 010 $a3-031-52645-7 024 7 $a10.1007/978-3-031-52645-9 035 $a(CKB)30597583400041 035 $a(MiAaPQ)EBC31200863 035 $a(Au-PeEL)EBL31200863 035 $a(DE-He213)978-3-031-52645-9 035 $a(EXLCZ)9930597583400041 100 $a20240228d2024 u| 0 101 0 $aeng 135 $aur||||||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aSmart Big Data in Digital Agriculture Applications $eAcquisition, Advanced Analytics, and Plant Physiology-informed Artificial Intelligence /$fby Haoyu Niu, YangQuan Chen 205 $a1st ed. 2024. 210 1$aCham :$cSpringer Nature Switzerland :$cImprint: Springer,$d2024. 215 $a1 online resource (243 pages) 225 1 $aAgriculture Automation and Control,$x2731-3506 311 $a3-031-52644-9 320 $aIncludes bibliographical references and index. 327 $aPart I Why Big Data Is Not Smart Yet? -- 1. Introduction -- 2. Why Do Big Data and Machine Learning Entail the Fractional Dynamics? -- Part II Smart Big Data Acquisition Platforms -- 3. Small Unmanned Aerial Vehicles (UAVs) and Remote Sensing Payloads -- 4. The Edge-AI Sensors and Internet of Living Things (IoLT) -- 5. The Unmanned Ground Vehicles (UGVs) for Digital Agriculture -- Part III Advanced Big Data Analytics, Plant Physiology-informed Machine Learning, and Fractional-order Thinking -- 6. Fundamentals of Big Data, Machine Learning, and Computer VisionWorkflow -- 7. A Low-cost Proximate Sensing Method for Early Detection of Nematodes inWalnut Using Machine Learning Algorithms -- 8. Tree-level Evapotranspiration Estimation of Pomegranate Trees Using Lysimeter and UAV Multispectral Imagery -- 9. Individual Tree-level Water Status Inference Using High-resolution UAV Thermal Imagery and Complexity-informed Machine Learning -- 10. Scale-aware Pomegranate Yield Prediction Using UAV Imagery and Machine Learning -- Part IV Towards Smart Big Data in Digital Agriculture -- 11. Intelligent Bugs Mapping and Wiping (iBMW): An Affordable Robot-Driven Robot for Farmers -- 12. A Non-invasive Stem Water Potential Monitoring Method Using Proximate Sensor and Machine Learning Classification Algorithms -- 13. A Low-cost Soil Moisture Monitoring Method by Using Walabot and Machine Learning Algorithms -- 14. Conclusions and Future Research. 330 $aIn the dynamic realm of digital agriculture, the integration of big data acquisition platforms has sparked both curiosity and enthusiasm among researchers and agricultural practitioners. This book embarks on a journey to explore the intersection of artificial intelligence and agriculture, focusing on small-unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), edge-AI sensors and the profound impact they have on digital agriculture, particularly in the context of heterogeneous crops, such as walnuts, pomegranates, cotton, etc. For example, lightweight sensors mounted on UAVs, including multispectral and thermal infrared cameras, serve as invaluable tools for capturing high-resolution images. Their enhanced temporal and spatial resolutions, coupled with cost effectiveness and near-real-time data acquisition, position UAVs as an optimal platform for mapping and monitoring crop variability in vast expanses. This combination of data acquisition platforms and advanced analytics generates substantial datasets, necessitating a deep understanding of fractional-order thinking, which is imperative due to the inherent ?complexity? and consequent variability within the agricultural process. Much optimism is vested in the field of artificial intelligence, such as machine learning (ML) and computer vision (CV), where the efficient utilization of big data to make it ?smart? is of paramount importance in agricultural research. Central to this learning process lies the intricate relationship between plant physiology and optimization methods. The key to the learning process is the plant physiology and optimization method. Crafting an efficient optimization method raises three pivotal questions: 1.) What represents the best approach to optimization? 2.) How can we achieve a more optimal optimization? 3.) Is it possible to demand ?more optimal machine learning,? exemplified by deep learning, while minimizing the need for extensive labeled data for digital agriculture? This book details the foundations of the plant physiology-informed machine learning (PPIML) and the principle of tail matching (POTM) framework. It is the 9th title of the "Agriculture Automation and Control" book series published by Springer. 410 0$aAgriculture Automation and Control,$x2731-3506 606 $aAgriculture 606 $aPlant physiology 606 $aQuantitative research 606 $aEngineering design 606 $aAgriculture 606 $aPlant Physiology 606 $aData Analysis and Big Data 606 $aEngineering Design 615 0$aAgriculture. 615 0$aPlant physiology. 615 0$aQuantitative research. 615 0$aEngineering design. 615 14$aAgriculture. 615 24$aPlant Physiology. 615 24$aData Analysis and Big Data. 615 24$aEngineering Design. 676 $a338.10285 700 $aNiu$b Haoyu$01263980 702 $aChen$b YangQuan 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910842292703321 996 $aSmart Big Data in Digital Agriculture Applications$94237393 997 $aUNINA