1
|
Improving Biomass and Grain Yield Prediction of Wheat Genotypes on Sodic Soil Using Integrated High-Resolution Multispectral, Hyperspectral, 3D Point Cloud, and Machine Learning Techniques. REMOTE SENSING 2021. [DOI: 10.3390/rs13173482] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Sodic soils adversely affect crop production over extensive areas of rain-fed cropping worldwide, with particularly large areas in Australia. Crop phenotyping may assist in identifying cultivars tolerant to soil sodicity. However, studies to identify the most appropriate traits and reliable tools to assist crop phenotyping on sodic soil are limited. Hence, this study evaluated the ability of multispectral, hyperspectral, 3D point cloud, and machine learning techniques to improve estimation of biomass and grain yield of wheat genotypes grown on a moderately sodic (MS) and highly sodic (HS) soil sites in northeastern Australia. While a number of studies have reported using different remote sensing approaches and crop traits to quantify crop growth, stress, and yield variation, studies are limited using the combination of these techniques including machine learning to improve estimation of genotypic biomass and yield, especially in constrained sodic soil environments. At close to flowering, unmanned aerial vehicle (UAV) and ground-based proximal sensing was used to obtain remote and/or proximal sensing data, while biomass yield and crop heights were also manually measured in the field. Grain yield was machine-harvested at maturity. UAV remote and/or proximal sensing-derived spectral vegetation indices (VIs), such as normalized difference vegetation index, optimized soil adjusted vegetation index, and enhanced vegetation index and crop height were closely corresponded to wheat genotypic biomass and grain yields. UAV multispectral VIs more closely associated with biomass and grain yields compared to proximal sensing data. The red-green-blue (RGB) 3D point cloud technique was effective in determining crop height, which was slightly better correlated with genotypic biomass and grain yield than ground-measured crop height data. These remote sensing-derived crop traits (VIs and crop height) and wheat biomass and grain yields were further simulated using machine learning algorithms (multitarget linear regression, support vector machine regression, Gaussian process regression, and artificial neural network) with different kernels to improve estimation of biomass and grain yield. The artificial neural network predicted biomass yield (R2 = 0.89; RMSE = 34.8 g/m2 for the MS and R2 = 0.82; RMSE = 26.4 g/m2 for the HS site) and grain yield (R2 = 0.88; RMSE = 11.8 g/m2 for the MS and R2 = 0.74; RMSE = 16.1 g/m2 for the HS site) with slightly less error than the others. Wheat genotypes Mitch, Corack, Mace, Trojan, Lancer, and Bremer were identified as more tolerant to sodic soil constraints than Emu Rock, Janz, Flanker, and Gladius. The study improves our ability to select appropriate traits and techniques in accurate estimation of wheat genotypic biomass and grain yields on sodic soils. This will also assist farmers in identifying cultivars tolerant to sodic soil constraints.
Collapse
|
2
|
Morpho-Physiological Responses of Pisum sativum L. to Different Light-Emitting Diode (LED) Light Spectra in Combination with Biochar Amendment. AGRONOMY-BASEL 2020. [DOI: 10.3390/agronomy10030398] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Light quality and nutrient availability are the primary factors that influence plant growth and development. In a research context of improving indoor plant cultivation while lowering environmental impact practices, we investigated the effect of different light spectra, three provided by light-emitting diodes (LEDs), and one by a fluorescent lamp, on the morpho-physiology of Pisum sativum L. seedlings grown in the presence/absence of biochar. We found that all morpho-physiological traits are sensitive to changes in the red-to-far-red light (R:FR) ratio related to the light spectra used. In particular, seedlings that were grown with a LED type characterized by the lowest R:FR ratio (~2.7; AP67), showed good plant development, both above- and belowground, especially when biochar was present. Biochar alone did not affect the physiological traits, which were influenced by the interplay with lighting type. AP67 LED type had a negative impact only on leaf fluorescence emission in light conditions, which was further exacerbated by the addition of biochar to the growing media. However, we found that the combination of biochar with a specific optimal light spectrum may have a synergetic effect enhancing pea seedling physiological performances and fruit yield and fostering desired traits. This is a promising strategy for indoor plant production while respecting the environment.
Collapse
|
3
|
Abstract
Research Highlights: One of the ways to improve the quality of a seedlot used in the forest nursery is the grading of seed by colour. Background and Objectives: The study is intended for forest’s engineers and owners because it offers an alternative solution for forest seeds improvement before sowing. The success of forest establishment program mainly depends on the quality of Forest Reproductive Material. At this time usual practices during the seed processing is seed grading on size. This causes a lot of controversy about the possible reduction of genetic diversity through directional selection. Materials and Methods: Aiming to study the effect of seed coat colour on seedling performance, a one-year old container seedlings of Pinus sylvestris L. were planted at the post-fire site. Seedlings were produced from three fractions, previously graded in the visible wavelength range on a standard optical separator, plus control obtained without separation by colour. Results: Seedlings from different seed fractions performed differently in the first growing season after planting on the field. Seedlings from light seed fraction grow better in height, but those from dark seed fraction resulted with the highest survival rate. Light-dark seeds, which constitute the largest group in the initial sample by absolute weight, resulted with seedlings of the lowest growth rates and survival. The good results showed by seedlings from the control, for both growth rates and survival, indicate the weak effect of seed colour grading on seedlings field performance, but also the need for the more comprehensive studies in the future.
Collapse
|
4
|
Mochida K, Koda S, Inoue K, Hirayama T, Tanaka S, Nishii R, Melgani F. Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective. Gigascience 2019; 8:5232233. [PMID: 30520975 PMCID: PMC6312910 DOI: 10.1093/gigascience/giy153] [Citation(s) in RCA: 45] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2018] [Revised: 09/06/2018] [Accepted: 11/24/2018] [Indexed: 11/29/2022] Open
Abstract
Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.
Collapse
Affiliation(s)
- Keiichi Mochida
- Bioproductivity Informatics Research Team, RIKEN Center for Sustainable Resource Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
- Microalgae Production Control Technology Laboratory, RIKEN Baton Zone Program, RIKEN Cluster for Science, Technology and Innovation Hub, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
- Institute of Plant Science and Resources, Okayama University, 2-20-1 Chuo, Kurashiki, Okayama 710-0046, Japan
- Kihara Institute for Biological Research, Yokohama City University, 641-12 Maioka-cho, Totsuka-ku, Yokohama, Kanagawa 244–0813, Japan
- Graduate School of Nanobioscience, Yokohama City University, 22-2 Seto, Kanazawa-ku, Yokohama, Kanagawa 236-0027, Japan
| | - Satoru Koda
- Graduate School of Mathematics, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan
| | - Komaki Inoue
- Bioproductivity Informatics Research Team, RIKEN Center for Sustainable Resource Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
| | - Takashi Hirayama
- Institute of Plant Science and Resources, Okayama University, 2-20-1 Chuo, Kurashiki, Okayama 710-0046, Japan
| | - Shojiro Tanaka
- Hiroshima University of Economics, 5-37-1, Gion, Asaminami, Hiroshima-shi Hiroshima 731-0138, Japan
| | - Ryuei Nishii
- Institute of Mathematics for Industry, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan
| | - Farid Melgani
- Department of Information Engineering and Computer Science, University of Trento, Via Sommarive 9, 38123 Trento, Italy
| |
Collapse
|
5
|
Mochida K, Koda S, Inoue K, Hirayama T, Tanaka S, Nishii R, Melgani F. Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective. Gigascience 2019. [PMID: 30520975 DOI: 10.1093/gigascience/giy153/5232233] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/04/2023] Open
Abstract
Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.
Collapse
Affiliation(s)
- Keiichi Mochida
- Bioproductivity Informatics Research Team, RIKEN Center for Sustainable Resource Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
- Microalgae Production Control Technology Laboratory, RIKEN Baton Zone Program, RIKEN Cluster for Science, Technology and Innovation Hub, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
- Institute of Plant Science and Resources, Okayama University, 2-20-1 Chuo, Kurashiki, Okayama 710-0046, Japan
- Kihara Institute for Biological Research, Yokohama City University, 641-12 Maioka-cho, Totsuka-ku, Yokohama, Kanagawa 244-0813, Japan
- Graduate School of Nanobioscience, Yokohama City University, 22-2 Seto, Kanazawa-ku, Yokohama, Kanagawa 236-0027, Japan
| | - Satoru Koda
- Graduate School of Mathematics, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan
| | - Komaki Inoue
- Bioproductivity Informatics Research Team, RIKEN Center for Sustainable Resource Science, 1-7-22 Suehiro-cho, Tsurumi-ku, Yokohama, Kanagawa 230-0045, Japan
| | - Takashi Hirayama
- Institute of Plant Science and Resources, Okayama University, 2-20-1 Chuo, Kurashiki, Okayama 710-0046, Japan
| | - Shojiro Tanaka
- Hiroshima University of Economics, 5-37-1, Gion, Asaminami, Hiroshima-shi Hiroshima 731-0138, Japan
| | - Ryuei Nishii
- Institute of Mathematics for Industry, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan
| | - Farid Melgani
- Department of Information Engineering and Computer Science, University of Trento, Via Sommarive 9, 38123 Trento, Italy
| |
Collapse
|
6
|
Duan L, Han J, Guo Z, Tu H, Yang P, Zhang D, Fan Y, Chen G, Xiong L, Dai M, Williams K, Corke F, Doonan JH, Yang W. Novel Digital Features Discriminate Between Drought Resistant and Drought Sensitive Rice Under Controlled and Field Conditions. FRONTIERS IN PLANT SCIENCE 2018; 9:492. [PMID: 29719548 PMCID: PMC5913589 DOI: 10.3389/fpls.2018.00492] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/17/2017] [Accepted: 04/03/2018] [Indexed: 05/21/2023]
Abstract
Dynamic quantification of drought response is a key issue both for variety selection and for functional genetic study of rice drought resistance. Traditional assessment of drought resistance traits, such as stay-green and leaf-rolling, has utilized manual measurements, that are often subjective, error-prone, poorly quantified and time consuming. To relieve this phenotyping bottleneck, we demonstrate a feasible, robust and non-destructive method that dynamically quantifies response to drought, under both controlled and field conditions. Firstly, RGB images of individual rice plants at different growth points were analyzed to derive 4 features that were influenced by imposition of drought. These include a feature related to the ability to stay green, which we termed greenness plant area ratio (GPAR) and 3 shape descriptors [total plant area/bounding rectangle area ratio (TBR), perimeter area ratio (PAR) and total plant area/convex hull area ratio (TCR)]. Experiments showed that these 4 features were capable of discriminating reliably between drought resistant and drought sensitive accessions, and dynamically quantifying the drought response under controlled conditions across time (at either daily or half hourly time intervals). We compared the 3 shape descriptors and concluded that PAR was more robust and sensitive to leaf-rolling than the other shape descriptors. In addition, PAR and GPAR proved to be effective in quantification of drought response in the field. Moreover, the values obtained in field experiments using the collection of rice varieties were correlated with those derived from pot-based experiments. The general applicability of the algorithms is demonstrated by their ability to probe archival Miscanthus data previously collected on an independent platform. In conclusion, this image-based technology is robust providing a platform-independent tool for quantifying drought response that should be of general utility for breeding and functional genomics in future.
Collapse
Affiliation(s)
- Lingfeng Duan
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Jiwan Han
- National Plant Phenomics Centre, Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, United Kingdom
| | - Zilong Guo
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Haifu Tu
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Peng Yang
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Dong Zhang
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Yuan Fan
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Guoxing Chen
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Lizhong Xiong
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Mingqiu Dai
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| | - Kevin Williams
- National Plant Phenomics Centre, Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, United Kingdom
| | - Fiona Corke
- National Plant Phenomics Centre, Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, United Kingdom
| | - John H. Doonan
- National Plant Phenomics Centre, Institute of Biological, Environmental and Rural Sciences, Aberystwyth University, Aberystwyth, United Kingdom
| | - Wanneng Yang
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, College of Engineering, Huazhong Agricultural University, Wuhan, China
| |
Collapse
|
7
|
Assessment of Selected Parameters of the Automatic Scarification Device as an Example of a Device for Sustainable Forest Management. SUSTAINABILITY 2017. [DOI: 10.3390/su9122370] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
8
|
Feng H, Chen G, Xiong L, Liu Q, Yang W. Accurate Digitization of the Chlorophyll Distribution of Individual Rice Leaves Using Hyperspectral Imaging and an Integrated Image Analysis Pipeline. FRONTIERS IN PLANT SCIENCE 2017; 8:1238. [PMID: 28791031 PMCID: PMC5524744 DOI: 10.3389/fpls.2017.01238] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/30/2016] [Accepted: 06/30/2017] [Indexed: 05/20/2023]
Abstract
Pigments absorb light, transform it into energy, and provide reaction sites for photosynthesis; thus, the quantification of pigment distribution is vital to plant research. Traditional methods for the quantification of pigments are time-consuming and not suitable for the high-throughput digitization of rice pigment distribution. In this study, using a hyperspectral imaging system, we developed an integrated image analysis pipeline for automatically processing enormous amounts of hyperspectral data. We also built models for accurately quantifying 4 pigments (chlorophyll a, chlorophyll b, total chlorophyll and carotenoid) from rice leaves and determined the important bands (700-760 nm) associated with these pigments. At the tillering stage, the R2 values and mean absolute percentage errors of the models were 0.827-0.928 and 6.94-12.84%, respectively. The hyperspectral data and these models can be combined for digitizing the distribution of the chlorophyll with high resolution (0.11 mm/pixel). In summary, the integrated hyperspectral image analysis pipeline and selected models can be used to quantify the chlorophyll distribution in rice leaves. The use of this technique will benefit rice functional genomics and rice breeding.
Collapse
Affiliation(s)
- Hui Feng
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, and College of Engineering, Huazhong Agricultural UniversityWuhan, China
- Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Ministry of Education for Biomedical Photonics, Department of Biomedical Engineering, Huazhong University of Science and TechnologyWuhan, China
| | - Guoxing Chen
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, and College of Engineering, Huazhong Agricultural UniversityWuhan, China
| | - Lizhong Xiong
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, and College of Engineering, Huazhong Agricultural UniversityWuhan, China
| | - Qian Liu
- Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, and Key Laboratory of Ministry of Education for Biomedical Photonics, Department of Biomedical Engineering, Huazhong University of Science and TechnologyWuhan, China
| | - Wanneng Yang
- National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, Agricultural Bioinformatics Key Laboratory of Hubei Province, and College of Engineering, Huazhong Agricultural UniversityWuhan, China
| |
Collapse
|
9
|
Smirnakou S, Ouzounis T, Radoglou KM. Continuous Spectrum LEDs Promote Seedling Quality Traits and Performance of Quercus ithaburensis var. macrolepis. FRONTIERS IN PLANT SCIENCE 2017; 8:188. [PMID: 28261244 PMCID: PMC5306215 DOI: 10.3389/fpls.2017.00188] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/04/2016] [Accepted: 01/30/2017] [Indexed: 05/27/2023]
Abstract
Regulation of the growth, development, and quality of plants by the control of light quality has attracted extensive attention worldwide. The aim of this study was to examine the effects of continuous LED spectrum for indoor plant pre-cultivation and to investigate the morphological and physiological responses of a common broadleaved tree species in Mediterranean environment, Quercus ithaburensis var. macrolepis at seedling developmental stage. Thus, the seedlings were pre-cultivated for 28 days, under five different LED light qualities: (1) Fluorescent (FL) as control light (2) L20AP67 (high in green and moderate in far-red), (3) AP673L (high in green and red), (4) G2 (highest in red and far-red), AP67 (high in blue, red, and far-red), and (5) NS1 (highest in blue and green and lowest in far-red) LEDs. Further examination was held at the nursery for 1 year, on several seedling quality traits. Indeed, AP67 and AP673L triggered higher leaf formation, while L20AP67 positively affected seedling shoot development. NS1 and AP67 LED pre-cultivated seedlings showed significantly higher root fibrosity than those of FL light. Furthermore, NS1 and AP673L LEDs induced fourfold increase on seedling root dry weight than FL light. Hence, evaluating the seedling nursery performance attributes, most of those photomorphogenetic responses previously obtained were still detectable. Even more so, LED pre-cultivated seedlings showed higher survival and faster growth indicating better adaptation even under natural light conditions, a fact further reinforced by the significantly higher Dickson's quality index acquired. In conclusion, the goal of each nursery management program is the production of high quality seedlings with those desirable traits, which in turn satisfy the specific needs for a particular reforestation site. Thus, the enhanced oak seedling quality traits formed under continuous LEDs spectrum especially of NS1 and AP673L pre-cultivation may potentially fulfill this goal.
Collapse
Affiliation(s)
- Sonia Smirnakou
- Department of Forestry and Management of the Environment and Natural Resources, Democritus University of ThraceNea Orestiada, Greece
| | - Theoharis Ouzounis
- Horticulture and Product Physiology Group, Department of Plant Sciences, Wageningen UniversityWageningen, Netherlands
| | - Kalliopi M. Radoglou
- Department of Forestry and Management of the Environment and Natural Resources, Democritus University of ThraceNea Orestiada, Greece
| |
Collapse
|