Increasing cassava root yield on farmers' fields in Nigeria through appropriate weed management

Although cassava is recognized for its high tolerance to drought, irrigation is showing satisfactory results. However, few studies have been carried out to determine the effects of soil cover, irrigation and the combination of both on crop development. Theobjective of this study was to determine the influence of irrigation and plastic soil cover on the agronomic performance of sweet cassava. The planting was done in beds, in thedouble row system with the stem cutingsimplanted vertically, with 0.60m between rows and 0.80 m between plants. The following treatments were applied: naked non-irrigated bedding, bedding covered with non-irrigated black polyethylene plastic, naked bedding with irrigation and bedding covered with irrigated black polyethylene plastic. Irrigation wasperformedby conventional sprinkling, based on the daily soil water balance at the effective depth of the cassava root system in the different stages of crop development. The characters evaluated were: shoot weight, root yield, starch percentage in the roots and time for cooking. The expression of the characters shoot weight, root yield and starch percentage in the roots wassignificantly influenced by irrigation managementandsoil cover. The individual use of irrigation and plastic soilcover technologies led to increases in root yieldof 55% and 13%, respectively, and when used together, root yieldincreased by 89%.

Download Full-text

Innovative strategies for on-farm weed management in organic carrot

Renewable Agriculture and Food Systems ◽

10.1017/s1742170507001810 ◽

2007 ◽

Vol 22 (4) ◽

pp. 246-259 ◽

Cited By ~ 12

Author(s):

Andrea Peruzzi ◽

Marco Ginanni ◽

Marco Fontanelli ◽

Michele Raffaelli ◽

Paolo Bàrberi

Keyword(s):

Weed Control ◽

Weed Management ◽

Management System ◽

Root Yield ◽

Gross Margin ◽

Labor Time ◽

Innovative System ◽

Yield Quality ◽

Hand Weeding ◽

Physical Weed Control

AbstractWeed management is often the most troublesome technical problem to be solved in organic farming, especially in poorly competitive crops like vegetables. A four-year (2000–2003) series of trials was established to assess the possibility of adopting an innovative non-chemical weed management system in organic carrot grown on the Fucino plateau, i.e., the most important carrot-growing area in Italy. The system utilized for physical weed control was based first on a false seedbed technique followed by pre-sowing weed removal, performed with a special 2 m wide 6-row spring-tine harrow. Prior to crop emergence, a pass with a flame weeder equipped with four 50 cm wide-open flame burners was also performed. Post-emergence weed control consisted of one or more hoeing passes with a purpose-designed 11-tine precision hoe equipped with spring implements (torsion weeders and vibrating tines), in addition to hand weeding. This innovative system was applied to a novel planting pattern (sowing in ten individual rows within 2 m wide beds) and compared to the standard management system of the area (sowing within 2 m wide beds but in five bands, use of spring-tine harrowing and flame weeding pre-emergence and of traditional hoeing post-emergence). The new system was tested in different commercial farms including both early and late-sown carrot. Assessments included machine operative characteristics, labor time, weed density and biomass, crop root yield and yield quality, and economic data (physical weed control costs and crop gross margin). Compared to the standard system, the innovative system usually resulted in reduced labor time (from 28 to 40%) and total costs for physical weed control (on average −416 € ha−1). Use of the precision hoe resulted in intra-row weed reduction ranging from 65 to 90%, which also led to a marked reduction in the labor required for hand weeding. In 2001 the two systems did not differ in terms of yield and yield quality, whereas in 2002 and 2003 the innovative system showed a higher mean density of carrot plants (from 28 to 55%), root yield (from 30 to 42%), and gross margin (from 40 to 100%). Carrot yield was higher in farms which adopted an early sowing whereas root commercial quality was somewhat variable between systems and years. In general, results obtained with the innovative management system look very promising.

Download Full-text

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)

10.21203/rs.2.24148/v2 ◽

2020 ◽

Author(s):

Michael Gomez Selvaraj ◽

Manuel Valderrama ◽

Diego Guzman ◽

Milton Valencia ◽

Henry Ruiz ◽

...

Keyword(s):

Machine Learning ◽

Image Processing ◽

Image Analysis ◽

Vegetation Indices ◽

Analytical Framework ◽

Aerial Image ◽

Root Yield ◽

Breeding Programs ◽

Cassava Root ◽

Below Ground

Abstract Background: Rapid non-destructive measurements to predict cassava root yield over the full growing season through large numbers of germplasm and multiple environments is a huge challenge in Cassava breeding programs. As opposed to waiting until the harvest season, multispectral imagery using unmanned aerial vehicles (UAV) are capable of measuring the canopy metrics and vegetation indices (VIs) traits at different time points of the growth cycle. This resourceful time series aerial image processing with appropriate analytical framework is very important for the automatic extraction of phenotypic features from the image data. Many studies have demonstrated the usefulness of advanced remote sensing technologies coupled with machine learning (ML) approaches for accurate prediction of valuable crop traits. Until now, Cassava has received little to no attention in aerial image-based phenotyping and ML model testing. Results: To accelerate image processing, an automated image-analysis framework called CIAT Pheno-i was developed to extract plot level vegetation indices/canopy metrics. Multiple linear regression models were constructed at different key growth stages of cassava, using ground-truth data and vegetation indices obtained from a multispectral sensor. Henceforth, the spectral indices/features were combined to develop models and predict cassava root yield using different Machine learning techniques. Our results showed that (1) Developed CIAT pheno-i image analysis framework was found to be easier and more rapid than manual methods. (2) The correlation analysis of four phenological stages of cassava revealed that elongation (EL) and late bulking (LBK) were the most useful stages to estimate above-ground biomass (AGB), below-ground biomass (BGB) and canopy height (CH). (3) The multi-temporal analysis revealed that cumulative image feature information of EL+early bulky (EBK) stages showed a higher significant correlation (r = 0.77) for Green Normalized Difference Vegetation indices (GNDVI) with BGB than individual time points. Canopy height measured on the ground correlated well with UAV (CHuav)-based measurements (r = 0.92) at late bulking (LBK) stage. Among different image features, normalized difference red edge index (NDRE) data were found to be consistently highly correlated (r = 0.65 to 0.84) with AGB at LBK stage. (4) Among the four ML algorithms used in this study, k-Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machine (SVM) showed the best performance for root yield prediction with the highest accuracy of R2 = 0.67, 0.66 and 0.64, respectively. Conclusion: UAV platforms, time series image acquisition, automated image analytical framework (CIAT Pheno-i), and key vegetation indices (VIs) to estimate phenotyping traits and root yield described in this work have great potential for use as a selection tool in the modern cassava breeding programs around the world to accelerate germplasm and varietal selection. The image analysis software (CIAT Pheno-i) developed from this study can be widely applicable to any other crop to extract phenotypic information rapidly.

Download Full-text

Early prediction models for cassava root yield in different water regimes

Field Crops Research ◽

10.1016/j.fcr.2019.05.017 ◽

2019 ◽

Vol 239 ◽

pp. 149-158 ◽

Cited By ~ 2

Author(s):

Alison Borges Vitor ◽

Rafael Parreira Diniz ◽

Carolina Vianna Morgante ◽

Rafaela Priscila Antônio ◽

Eder Jorge de Oliveira

Keyword(s):

Prediction Models ◽

Early Prediction ◽

Root Yield ◽

Water Regimes ◽

Cassava Root

Download Full-text

On-farm assessment of cassava root yield response to tillage, plant density, weed control and fertilizer application in southwestern Nigeria

Field Crops Research ◽

10.1016/j.fcr.2020.108038 ◽

2021 ◽

Vol 262 ◽

pp. 108038

Author(s):

Olabisi Omolara Onasanya ◽

Stefan Hauser ◽

Magdalena Necpalova ◽

Felix Kolawole Salako ◽

Christine Kreye ◽

...

Keyword(s):

Weed Control ◽

Plant Density ◽

Fertilizer Application ◽

Yield Response ◽

Root Yield ◽

Southwestern Nigeria ◽

Cassava Root ◽

On Farm

Download Full-text

Varietal response of cassava root yield components and root necrosis from cassava Brown streak disease to time of harvesting in Uganda

Crop Protection ◽

10.1016/j.cropro.2019.02.013 ◽

2019 ◽

Vol 120 ◽

pp. 58-66

Author(s):

E. Kanju ◽

V.N.E. Uzokwe ◽

P. Ntawuruhunga ◽

S. Tumwegamire ◽

J. Yabeja ◽

...

Keyword(s):

Yield Components ◽

Root Yield ◽

Cassava Root ◽

Root Necrosis ◽

Varietal Response ◽

Cassava Brown Streak Disease ◽

Brown Streak

Download Full-text

Trends in Food Crop Yields under Demographic Pressure in Sub-Saharan Africa: the Case of Cassava in Southeast Nigeria

Outlook on Agriculture ◽

10.1177/003072709502400409 ◽

1995 ◽

Vol 24 (4) ◽

pp. 249-254 ◽

Cited By ~ 2

Author(s):

Anselm A. Enete ◽

Felix I. Nweke ◽

Eugene C. Okorji

Keyword(s):

Population Density ◽

Large Population ◽

Sub Saharan Africa ◽

High Population ◽

High Population Density ◽

Root Yield ◽

National Team ◽

Cassava Root ◽

Density Area ◽

Cassava Plant

Research in 1973 attributed large cassava root yield differences among three villages in southeast Nigeria to equally large population density differences. In 1993, the Nigerian national team of the Collaborative Study of Cassava in Africa (COSCA) went back to the three villages to see whether population growth had led to yield declines. They found that the wide gap in yields between the high and low population density villages was maintained, apparently due to differences in soil type, fallow periods, cassava plant densities and harvest dates. Cassava root yield had doubled in the high population density area, increased but not doubled in the medium population density area and declined in the low population density area. The differences in the yield trends among the three villages were due to the use of improved cassava varieties in the high population density area.

Download Full-text

Liming and phosphorus fertilization increase cassava root yield without affecting its cooking time

Agronomy Journal ◽

10.1002/agj2.20842 ◽

2021 ◽

Author(s):

Ben‐Hur S. Rosa ◽

Adalton M. Fernandes ◽

Bruno Gazola ◽

Jesion G. S. Nunes ◽

Rogério P. Soratto

Keyword(s):

Cooking Time ◽

Phosphorus Fertilization ◽

Root Yield ◽

Cassava Root

Download Full-text

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)

10.21203/rs.2.24148/v3 ◽

2020 ◽

Author(s):

Michael Gomez Selvaraj ◽

Manuel Valderrama ◽

Diego Guzman ◽

Milton Valencia ◽

Henry Ruiz ◽

...

Keyword(s):

Machine Learning ◽

Image Processing ◽

Image Analysis ◽

Vegetation Indices ◽

Analytical Framework ◽

Aerial Image ◽

Root Yield ◽

Breeding Programs ◽

Cassava Root ◽

Below Ground

Abstract Background: Rapid non-destructive measurements to predict cassava root yield over the full growing season through large numbers of germplasm and multiple environments is a huge challenge in Cassava breeding programs. As opposed to waiting until the harvest season, multispectral imagery using unmanned aerial vehicles (UAV) are capable of measuring the canopy metrics and vegetation indices (VIs) traits at different time points of the growth cycle. This resourceful time series aerial image processing with appropriate analytical framework is very important for the automatic extraction of phenotypic features from the image data. Many studies have demonstrated the usefulness of advanced remote sensing technologies coupled with machine learning (ML) approaches for accurate prediction of valuable crop traits. Until now, Cassava has received little to no attention in aerial image-based phenotyping and ML model testing. Results : To accelerate image processing, an automated image-analysis framework called CIAT Pheno-i was developed to extract plot level vegetation indices/canopy metrics. Multiple linear regression models were constructed at different key growth stages of cassava, using ground-truth data and vegetation indices obtained from a multispectral sensor. Henceforth, the spectral indices/features were combined to develop models and predict cassava root yield using different Machine learning techniques. Our results showed that (1) Developed CIAT pheno-i image analysis framework was found to be easier and more rapid than manual methods. (2) The correlation analysis of four phenological stages of cassava revealed that elongation (EL) and late bulking (LBK) were the most useful stages to estimate above-ground biomass (AGB), below-ground biomass (BGB) and canopy height (CH). (3) The multi-temporal analysis revealed that cumulative image feature information of EL+early bulky (EBK) stages showed a higher significant correlation ( r = 0.77) for Green Normalized Difference Vegetation indices (GNDVI) with BGB than individual time points. Canopy height measured on the ground correlated well with UAV (CHuav)-based measurements ( r = 0.92) at late bulking (LBK) stage. Among different image features, normalized difference red edge index (NDRE) data were found to be consistently highly correlated ( r = 0.65 to 0.84) with AGB at LBK stage. (4) Among the four ML algorithms used in this study, k-Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machine (SVM) showed the best performance for root yield prediction with the highest accuracy of R 2 = 0.67, 0.66 and 0.64, respectively. Conclusion : UAV platforms, time series image acquisition, automated image analytical framework (CIAT Pheno-i), and key vegetation indices (VIs) to estimate phenotyping traits and root yield described in this work have great potential for use as a selection tool in the modern cassava breeding programs around the world to accelerate germplasm and varietal selection. The image analysis software (CIAT Pheno-i) developed from this study can be widely applicable to any other crop to extract phenotypic information rapidly.

Download Full-text