<p><span>This paper presents a system that helps farmers to irrigate crops, minimizing water consumption, while productivity is kept, when deficit irrigation techniques are applied, according to the phenological stage of such crop. Such stage is automatically inferred by using a Machine Learning-based technique, which uses single images, which can be acquired by simply using a low cost commercial camera (even the one embedded in a smartphone), as inputs. Specifically, this work compares several Machine Learning approaches, in particular, classical and deep neural networks trained with a dataset obtained from taking multiple real images from a citrus crop. Such images represent different growing stages of the citrus associated to different phenological stages. Since, according to the deficit irrigation approach, the amount of water that can be reduced without affecting the yield depends on the phenological stage of the crop, once such stage is inferred, a Decision Support System uses such information for automatically programming irrigation. The paper also remarks the main advantages of using a single camera as unique sensor in terms of low economic cost as opposed to other systems that uses more expensive and invasive sensors in the crop. In addition, as a smartphone camera could be used as sensor, the smartphone itself could be used as computing device to run the phenological stage detector in real time, and to interact with the Decision Support System by using Cloud and Edge computing technologies. Finally, a set of experiments show the main results obtained after testing different Machine Learning approaches. After comparing such approaches, the best choice is selected to be integrated as a part of the mentioned Decision Support System.</span></p>
<p>The sensitivity to water stress of different plant water indicators (PWI) at different plot scales (leaf and aerial) was evaluated during the second fruit growth stage of grapefruit (<em>Citrus paradisi</em> cv. Star Ruby) trees growing in a commercial orchard for a sustainable irrigation scheduling. Trees were drip-irrigated and submitted to two irrigation treatments: (i) a control (CTL), irrigated at 100% of crop evapotranspiration to avoid any soil water limitations, and (ii) a non-irrigated (NI) treatment, irrigated as the control until the 104 days after full bloom (DAFB) when the irrigation was suppressed, until to reach a severe water stress level in the plants (around -2.3 MPa of stem water potential at solar midday). The plant water indicators studied were: stem water potential (SWP); leaf conductance (Lc); net photosynthesis (Pn), and several vegetation indices (VI) in the visible spectral region derived from an unmanned aerial vehicle equipped with a multispectral sensor. The measurements were made at 9, 12 and 18h (solar time) on 50 and 134 DAFB, coinciding with a fruit diameter of 20 and 70 mm, respectively. The correlation analysis between the PWI at leaf scale (SWP, Lc and Pn) and at aerial scale showed relatively poor results, with Pearson correlation coefficients (r values) around 0.6. However, SWP presented the highest r value with the normalized difference vegetation index (NVDI), green index (GI), normalized difference greenness vegetation index (NDGI) and red green ratio index (RGRI) showing the higher coefficients 0.80, 0,80, 0.85 and 0.86, respectively. In addition, a quadratic regression curve fitting was made for the SWP and aforementioned indices, obtaining values &#8203;&#8203;of R<sup>2</sup> around 0.7 in all cases; the best fit corresponded to SWP = - 4.869 + 15.765 NDGI - 14.283 NDGI<sup>2</sup> (R<sup>2 </sup>= 0.749) to predict SWP values between -0.5 and -2.3 MPa. Results obtained show the possibility of using certain vegetation indices to be used in the detection of water stress in adult grapefruits, and thus propose a sustainable and efficient irrigation scheduling.</p><p>Funding:</p><p>-WATER4EVER is funded by the European Commission under the framework of the ERA-NET COFUND WATERWORKS 2015 Programme</p><p>-RIS3MUR REUSAGUA is funded by the Consejer&#237;a de Empresa, Industria y Portavoc&#237;a of the Murcia Region under the Feder Operational Program 2014-2020</p>
<p>The WATER4EVER Project (http://water4ever.eu/) was built on the premise that agriculture is by far the largest consumer of water, with about 70% of the diverted water being used in irrigation. Agriculture is also considered as a key source of diffuse pollution with inefficient practices resulting in high water and nutrient (particularly N and P) surpluses that are transferred to water bodies through diffuse processes (runoff and leaching), promoting eutrophication, with associated biodiversity loss. WATER4EVER aims thus to develop new monitoring strategies at the plot and catchment scales to provide detailed information of water and nutrient flow, and gain new insights on the connectivity between both scales. New monitoring strategies were developed and tested in agricultural fields in Portugal, Spain, Italy and Turkey and included: (i) crop physiological indicators assessment using static sensors for defining improved deficit irrigation strategies for woody crops; (ii) crop stress and productivity maps from measurements taken with a smart sensor mounted on a tractor and equipped with LIDAR 2D, normalized difference vegetation index (NDVI) and thermal cameras, and a GNSS receiver; (iii) leaf area index maps at 30 m resolution derived from ATCOR and Landsat 8 imagery data using the NDVI and the Soil Adjusted Vegetation Index (SAVI); (iv) soil moisture maps at 100 m resolution by combining the 10 m resolution synthetic-aperture radar (SAR) images from Sentinel 1 with the 10 m resolution NDVI computed from Sentinel 2 images, averaged into 100 m cells, and then by considering the backscatter difference with the driest day, or alternatively the backscatter difference between two consecutive dates; (v) soil moisture maps at 1 km resolution created with the DISaggregation based on a Physical And Theoretical scale CHange (DISPATCH) algorithm for the downscaling of the 40 km SMOS (Soil Moisture and Ocean Salinity) soil moisture data using land surface temperature (LST) and NDVI data; (vi) conventional monitoring techniques combined with modeling tools for assessing the impact of different soil managements (conventional tillage, tillage with grass trips, grass cover) on soil infiltration, soil water content, runoff and soil erosion of hillslope vineyards; (vii) an improved deterministic model for irrigation and fertigation management at the plot scale; and (viii) a decision support system for irrigation water management at the plot scale which integrated a deterministic model for irrigation scheduling and the NDVI computed from Sentinel 2 imagery data for crop growth monitoring. Preliminary results derived from the use of the innovative monitoring and mapping strategies, besides model applications are presented. The remote sensing products described above were also applied for catchment modeling validation of streamflow, which results fall outside the scope of this communication. WATER4EVER activities were thus wide and diverse, aimed at optimizing crop management practices which will help to promote the sustainability of different Mediterranean production systems.</p><p>&#160;</p><p>WATER4EVER is funded by the European Commission under the framework of the ERA-NET COFUND WATERWORKS 2015 Programme</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.