打印

作者

Madeleine Dubelko;Robert Schutzki;Jeffrey Andresen;Bert Cregg

来源

URBAN FORESTRY & URBAN GREENING,Vol.75,Issue1,Article 127688

语言

英文

关键字

作者单位

Michigan State University, Department of Horticulture, 1066 Bogue Street, East Lansing, MI 48824, USA;Michigan State University, Department of Geography, Environment, and Spatial Sciences, 673 Auditorium Road, East Lansing, MI 48824, USA;Michigan State University, Department of Forestry, 480 Wilson Road, East Lansing, MI 48824, USA;Michigan State University, Department of Horticulture, 1066 Bogue Street, East Lansing, MI 48824, USA;Michigan State University, Department of Geography, Environment, and Spatial Sciences, 673 Auditorium Road, East Lansing, MI 48824, USA;Michigan State University, Department of Forestry, 480 Wilson Road, East Lansing, MI 48824, USA;Key Laboratory of Smart Agriculture Systems Integration, Ministry of Education, China Agricultural University, Beijing 100083, PR China;Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing 100083, PR China;USDA-Agricultural Research Service, Soil and Water Conservation Research Unit, 48037 Tubbs Ranch Road, Adams, OR 97810, USA;Department of Crop and Soil Sciences, Washington State University, Dryland Research Station, PO Box B, 781 E. Experiment Station Road, Lind, WA, USA;Agricultural Engineering Department, UFLA Campus, Lavras, MG, 37200-000, Brazil;Sanitary and Environmental Engineering Department, UFMT Campus, Cuiabá, MT, 78060-900, Brazil;Phytopathology Department, UFLA Campus, Lavras, MG, 37200-000, Brazil;Soil Science Department, UFLA Campus, Lavras, MG, 37200-000, Brazil;Research Paper"}]},{"#name":"title","$":{"id":"title0010"},"_":"The role of machine learning on Arabica coffee crop yield based on remote sensing and mineral nutrition monitoring"}],"floats":[],"footnotes":[],"attachments":[]},"openArchive":false,"openAccess":false,"document-subtype":"fla","content-family":"serial","contentType":"JL","abstract":{"$$":[{"$$":[{"$$":[{"$$":[{"#name":"__text__","_":"Coffee yield variation in the field can be learned to obtain useful information for coffee management. Machine learning algorithms were evaluated to determine Arabica coffee yield. The Classification and Regression Tree (CART) rpart1SE algorithm used for classification and regression provided crucial nutrient thresholds to obtain high yield and minimise yield variability, by increasing vigour in well-nourished plants, with fertiliser management in the field. The use of the random forest model enabled to detect the most important variables for predicting coffee yield, as well as to identify how the nutritional status of the plants, such as Mg, Fe and Ca contents can be balanced to maximise yield. Variables related to the coffee nutritional status were more important than remote sensing variables for estimating coffee yield in the field. Despite the better accuracy of the random forest model (rf) to predict coffee yield when compared to the rpart1SE model, the particularity of each machine learning algorithm modelling was used in terms of the benefits of the results of each methodology synergistically in favour of wisely defining the best strategy and tactics for the crop management. In general, Mg leaf content was the most important variable for yield class prediction in both the 2005 and 2006 harvests by the rf model. The CART algorithm defined Mg leaf content threshold <3.615 g kg"},{"$":{"loc":"post"},"#name":"sup","_":"−1;Soil and Water Department, Faculty of Agriculture, Suez Canal University, Ismailia 41522, Egypt;Department of Environment, Faculty of Bioscience Engineering, Ghent University, Belgium;Faculty of Electrical Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia;Vocational School of Technical Sciences, Bursa Uludag University, Bursa, Turkey;Departamento de Ciencias Agrarias, Facultad de Ciencias Agrarias y Forestales, Universidad Católica del Maule, Curicó 3340000, Chile;Digital Agriculture Food and Wine Group, School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Parkville VIC 3010, Australia;Research and Extension Center for Irrigation and Agroclimatology (CITRA), Faculty of Agricultural Sciences, Universidad de Talca, Talca 3460000, Chile;Laboratory of Technological Research in Pattern Recognition (LITRP), Faculty of Engineering Science, Universidad Católica del Maule, Talca 3480112, Chile;National Engineering Laboratory of Integrated Transportation Big Data Application Technology, School of Transportation and Logistics, Southwest Jiaotong University, Chengdu 611756, China;Guangdong Communication Planning & Design Institute Group Co Ltd, Guangzhou 510507, China;The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, China

摘要

Establishment of roadside plantings is often limited by adverse site conditions, particularly poor soil physical and chemical properties. We compared plant establishment of shrubs, herbaceous perennials, and grasses in response to addition of compost and/or tillage before planting in replicated plots at two locations along an interstate highway near Detroit, MI, USA. Plots at each location received one of four site preparation treatments: control (no treatment), compost only (top-dressed with 8 cm of municipal compost), tillage only (soil tilled to 20 cm) or compost + tillage (8 cm of compost added and tilled to 20 cm). Within each site preparation plot, we established sub-plots of 16 selections of shrubs, perennials, and ornamental grasses. Compost addition, plant selection, and location affected (P ≤ 0.05) plant survival, height growth, and % plant cover two years after planting. Tillage did not affect (P &gt; 0.05) plant establishment. Similarly, the interaction of tillage × compost was not significant, indicating that surface application of compost was as effective as tilling compost into the soil. Improved plant establishment with the addition of compost was associated with improved soil and plant nutrition and reduced soil pH and soil bulk density. Within each plant group (i.e., shrubs, perennials, grasses) plant establishment varied widely. Overall, the results indicate that compost addition can improve establishment of diverse roadside plantings, which was associated with improved soil fertility. In contrast, tillage provided comparatively little benefit to plant performance in this trial.