Dynamic Bayesian network for crop growth prediction in greenhouses

Abstract The paper presents an Internet-of-Things based agricultural decision support system for crop growth. A dynamic Bayesian network (DBN) relates indicative parameters of crop development to environmental control parameters via unobserved (hidden) Markov states. The expectation-maximization algorithm is used to track the states and to learn the parameters of the DBN. The steady state information is then used to derive a predictor for the measurement data a few days ahead. The proposed DBN avoids time-consuming training cultivation cycles, as only data of the current cultivation cycle are available to the algorithm. Three cultivation cycles of lettuce have been used to test the performance of the proposed DBN. The environmental parameters were temperature, solar irradiance and vapor-pressure deficit. The measurement data include evapotranspiration at granularity equal one day, and leaf-area index and dry weight, at granularity equal one week. It turned out that accurate measurement data prediction a few days ahead is possible even if the number of data samples is low.

[1]  Alberto Pardossi,et al.  Sensor-based management of container nursery crops irrigated with fresh or saline water , 2019, Agricultural Water Management.

[2]  Stefano Chessa,et al.  Internet of Things for enabling smart environments: A technology-centric perspective , 2019, J. Ambient Intell. Smart Environ..

[3]  José Santa,et al.  Smart farming IoT platform based on edge and cloud computing , 2019, Biosystems Engineering.

[4]  C. Rama Krishna,et al.  An IoT based smart irrigation management system using Machine learning and open source technologies , 2018, Computers and Electronics in Agriculture.

[5]  Jirapond Muangprathub,et al.  IoT and agriculture data analysis for smart farm , 2019, Comput. Electron. Agric..

[6]  L. Bacci,et al.  Modelling transpiration of greenhouse gerbera (Gerbera jamesonii H. Bolus) grown in substrate with saline water in a Mediterranean climate , 2013 .

[7]  Giuseppe Pirlo,et al.  Machine Learning Applications on Agricultural Datasets for Smart Farm Enhancement , 2018, Machines.

[8]  Haihui Zhang,et al.  An adaptive fuzzy hierarchical control for maintaining solar greenhouse temperature , 2018, Comput. Electron. Agric..

[9]  D. P. Aikman,et al.  Growth of Lettuce, Onion and Red Beet. 2. Growth Modelling , 1996 .

[10]  J. Senthilnath,et al.  Detection of tomatoes using spectral-spatial methods in remotely sensed RGB images captured by UAV , 2016 .

[11]  R. Piton,et al.  Iterative joint channel estimation and successive interference cancellation using a SISO-SAGE algorithm for coded CDMA , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[12]  H. R. Soares,et al.  Lettuce growth and water consumption in NFT hydroponic system using brackish water , 2015 .

[13]  Shaozhong Kang,et al.  Water use efficiency is improved by alternate partial root-zone irrigation of apple in arid northwest China , 2017 .

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  E. J. van Henten,et al.  Validation of a dynamic lettuce growth model for greenhouse climate control. , 1994 .

[16]  Arnold J. Bloom,et al.  Easy Leaf Area: Automated digital image analysis for rapid and accurate measurement of leaf area1 , 2014, Applications in plant sciences.

[17]  Francisco M. Padilla,et al.  Determination of sufficiency values of canopy reflectance vegetation indices for maximum growth and yield of cucumber , 2017 .

[18]  Luca Incrocci,et al.  Simulation of crop water and mineral relations in greenhouse soilless culture , 2011, Environ. Model. Softw..

[19]  Alberto Pardossi,et al.  An aggregated model for water requirements of greenhouse tomato grown in closed rockwool culture with saline water , 2007 .

[20]  Yuki Sago,et al.  Quantitative Nutrient Management Reduces Nitrate Accumulation in Hydroponic Butterhead Lettuces Grown under Artificial Lighting , 2018, HortScience.

[21]  Suha Berberoglu,et al.  Biotope conservation in a Mediterranean agricultural land by incorporating crop modelling , 2019, Ecological Modelling.

[22]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[23]  Ido Seginer,et al.  SE—Structures and Environment: The Penman–Monteith Evapotranspiration Equation as an Element in Greenhouse Ventilation Design , 2002 .

[24]  Young K. Chang,et al.  Current and future applications of statistical machine learning algorithms for agricultural machine vision systems , 2019, Comput. Electron. Agric..

[25]  Gerald A. Carlson,et al.  A Decision Theoretic Approach to Crop Disease Prediction and Control , 1970 .

[26]  Xia Sun,et al.  State-of-the-Art Internet of Things in Protected Agriculture , 2019, Sensors.

[27]  Sanmeet Kaur,et al.  Evolution of Internet of Things (IoT) and its significant impact in the field of Precision Agriculture , 2019, Comput. Electron. Agric..

[28]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[29]  Simon Cook,et al.  Using Bayesian networks to predict future yield functions with data from commercial oil palm plantations: A proof of concept analysis , 2018, Comput. Electron. Agric..

[30]  A. Baille,et al.  A simplified model for predicting evapotranspiration rate of nine ornamental species vs. climate factors and leaf area , 1994 .

[31]  Jairo Alejandro Gomez,et al.  Review of IoT applications in agro-industrial and environmental fields , 2017, Comput. Electron. Agric..

[32]  Claudinei Fonseca Souza,et al.  Influence of the use of wastewater on nutrient absorption and production of lettuce grown in a hydroponic system , 2018 .

[33]  Guifen Chen,et al.  Bayesian Networks Modeling for Crop Diseases , 2010, CCTA.

[34]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.