Unsupervised domain adaptation for early detection of drought stress in hyperspectral images

Abstract Hyperspectral images can be used to uncover physiological processes in plants if interpreted properly. Machine Learning methods such as Support Vector Machines (SVM) and Random Forests have been applied to estimate development of biomass and detect and predict plant diseases and drought stress. One basic requirement of machine learning implies, that training and testing is done in the same domain and the same distribution. Different genotypes, environmental conditions, illumination and sensors violate this requirement in most practical circumstances. Here, we present an approach, which enables the detection of physiological processes by transferring the prior knowledge within an existing model into a related target domain, where no label information is available. We propose a two-step transformation of the target features, which enables a direct application of an existing model. The transformation is evaluated by an objective function including additional prior knowledge about classification and physiological processes in plants. We have applied the approach to three sets of hyperspectral images, which were acquired with different plant species in different environments observed with different sensors. It is shown, that a classification model, derived on one of the sets, delivers satisfying classification results on the transformed features of the other data sets. Furthermore, in all cases early non-invasive detection of drought stress was possible.

[1]  J. Dungan,et al.  Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: Testing the Kokaly and Clark methodologies , 2001 .

[2]  Elizabeth Pennisi,et al.  The Blue Revolution, Drop by Drop, Gene by Gene , 2008, Science.

[3]  A. Gitelson,et al.  Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation , 1994 .

[4]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[5]  Roberto Tuberosa,et al.  Genomics-based approaches to improve drought tolerance of crops. , 2006, Trends in plant science.

[6]  H. Bleiholder,et al.  Use of the extended BBCH scale—general for the descriptions of the growth stages of mono; and dicotyledonous weed species , 1997 .

[7]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[8]  John A. Gamon,et al.  Assessing leaf pigment content and activity with a reflectometer , 1999 .

[9]  Xia Li,et al.  Domain adaptation for land use classification: A spatio-temporal knowledge reusing method , 2014 .

[10]  S. Prasher,et al.  Application of support vector machine technology for weed and nitrogen stress detection in corn , 2006 .

[11]  J. R. Jensen.  Remote Sensing of the Environment: An Earth Resource Perspective , 2000 .

[12]  Jaime S. Cardoso,et al.  Measuring the Performance of Ordinal Classification , 2011, Int. J. Pattern Recognit. Artif. Intell..

[13]  B. Datt.  Remote Sensing of Chlorophyll a, Chlorophyll b, Chlorophyll a+b, and Total Carotenoid Content in Eucalyptus Leaves , 1998 .

[14]  A. Gitelson,et al.  Optical Properties and Nondestructive Estimation of Anthocyanin Content in Plant Leaves¶ , 2001, Photochemistry and photobiology.

[15]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[16]  A. Gitelson,et al.  Non‐destructive optical detection of pigment changes during leaf senescence and fruit ripening , 1999 .

[17]  C. Spearman.  The proof and measurement of association between two things. By C. Spearman, 1904. , 1987, The American journal of psychology.

[18]  L. Plümer,et al.  Robust fitting of fluorescence spectra for pre-symptomatic wheat leaf rust detection with Support Vector Machines , 2011 .

[19]  L. Plümer,et al.  ORDINAL CLASSIFICATION FOR EFFICIENT PLANT STRESS PREDICTION IN HYPERSPECTRAL DATA , 2014 .

[20]  N. Turner.  Measurement of plant water status by the pressure chamber technique , 1988, Irrigation Science.

[21]  Bernhard Schölkopf,et al.  Correcting Sample Selection Bias by Unlabeled Data , 2006, NIPS.

[22]  L. Plümer,et al.  Detection of early plant stress responses in hyperspectral images , 2014 .

[23]  Ramesh Nallapati,et al.  A Comparative Study of Methods for Transductive Transfer Learning , 2007 .

[24]  P. F. Scholander,et al.  Sap Pressure in Vascular Plants , 1965, Science.

[25]  D. Sims,et al.  Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages , 2002 .

[26]  D. M. Moss,et al.  Red edge spectral measurements from sugar maple leaves , 1993 .

[27]  John Blitzer,et al.  Domain Adaptation with Coupled Subspaces , 2011, AISTATS.

[28]  Panos M. Pardalos,et al.  A survey of data mining techniques applied to agriculture , 2009, Oper. Res..

[29]  A. Huete,et al.  A comparison of vegetation indices over a global set of TM images for EOS-MODIS , 1997 .

[30]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[31]  Eibe Frank,et al.  A Simple Approach to Ordinal Classification , 2001, ECML.

[32]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[34]  A. Gitelson,et al.  Assessing Carotenoid Content in Plant Leaves with Reflectance Spectroscopy¶ , 2002, Photochemistry and photobiology.

[35]  Gabriele Moser,et al.  Multimodal Classification of Remote Sensing Images: A Review and Future Directions , 2015, Proceedings of the IEEE.

[36]  Lorenzo Bruzzone,et al.  Toward the Automatic Updating of Land-Cover Maps by a Domain-Adaptation SVM Classifier and a Circular Validation Strategy , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[37]  C. Field,et al.  A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency , 1992 .

[38]  K. Kersting,et al.  Early drought stress detection in cereals: simplex volume maximisation for hyperspectral image analysis. , 2012, Functional plant biology : FPB.

[39]  Jörn Ostermann,et al.  BOOSTED UNSUPERVISED MULTI-SOURCE SELECTION FOR DOMAIN ADAPTATION , 2017 .

[40]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[41]  Gustavo Camps-Valls,et al.  Semisupervised Manifold Alignment of Multimodal Remote Sensing Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[42]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[43]  D. Tanré,et al.  Strategy for direct and indirect methods for correcting the aerosol effect on remote sensing: From AVHRR to EOS-MODIS , 1996 .

[44]  Scott Kirkpatrick,et al.  Optimization by Simmulated Annealing , 1983, Sci..

[45]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[46]  Christian Heipke,et al.  ITERATIVE RE-WEIGHTED INSTANCE TRANSFER FOR DOMAIN ADAPTATION , 2016 .

[47]  Lorenzo Bruzzone,et al.  Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.