Journal Articles
Permanent URI for this collection
Browse
Recent Submissions
Now showing 1 - 5 of 313
- ItemRandom Forest Machine Learning for Maize Yield and Agronomic Efficiency Prediction in Ghana(2024-08) Eric Asamoah; Gerard B.M. Heuvelink; Ikram Chairi; Bindraban, Prem S.; Vincent LogahMaize (Zea mays) is an important staple crop for food security in Sub-Saharan Africa. However,there is need to increase production to feed a growing population. In Ghana, this is mainly done by increasing acreage with adverse environmental consequences, rather than yield increment per unit area. Accurate prediction of maize yields and nutrient use efficiency in production is critical to making informed decisions toward economic and ecological sustainability. We trained the random forest machine learning algorithm to predict maize yield and agronomic efficiency in Ghana using soil, climate, environment, and management factors, including fertilizer application. We calibrated and evaluated the performance of the random forest machine learning algorithm using a 5 × 10-fold nested cross-validation approach. Data from 482 maize field trials consisting of 3136 georeferenced treatment plots conducted in Ghana from 1991 to 2020 were used to train the algorithm, identify important predictor variables, and quantify the uncertainties associated with the random forest predictions. The mean error, root mean squared error, model efficiency coefficient and 90 % prediction interval coverage probability were calculated. The results obtained on test data demonstrate good prediction performance for yield (MEC = 0.81) and moderate performance for agronomic efficiency (MEC = 0.63, 0.55 and 0.54 for AE-N, AE-P and AE-K, respectively). We found that climatic variables were less important predictors than soil variables for yield prediction, but temperature was of key importance to yield prediction and rainfall to agronomic efficiency. The developed random forest models provided a better understanding of the drivers of maize yield and agronomic efficiency in a tropical climate and an insight towards improving fertilizer recommendations for sustainable maize production and food security in Sub-Saharan Africa.
- ItemImpact of Tillage and Crop Establishment Methods on Crop Yields, Profitability and Soil Physical Properties in Rice –Wheat System of Indo-Gangetic Plains of India(2014) Vivak Kumar; Yashpal Singh Saharawat; Mahesh K. Gathala; C.M. Parihar; Rajeev Kumar; Robin Kumar; Mangi Lal Jat; A. S. Jat; D.M. Mahala; Lalit Kumar; Hari Sankar Nayak; M.D. Parihar; V.Rai; H.R. Jewlia; B.R. KuriConservation agriculture (CA) based on best-bet crop management practices may increase crop and water productivity, as well as conserve and sustain soil health and natural resources. In a 2-year profitability and soil physical properties in a rice –wheat (RW) system. The six TCE treatments were used to study the impact, which are puddled transplanted rice followed by conventionally tilled wheat (CTPR –CTW), direct seeded rice on the flat followed by zero till wheat (CTDSR –ZTW), zero till direct seeded rice with residue followed by zero till wheat with residue (ZTDSR+R –ZTW+R), transplanted rice after rotavator puddling followed by zero till wheat (RTTPR –ZTW), transplanted rice after rotavator puddling followed by rotary till wheat (RTTPR –RTW) and farmer practice rice – wheat (FP – RW). Result of the study revealed that mean rice yield was not significantly affected by different TCE methods. Wheat planted with ZTDSR+R –ZTW+R gave 30% larger grain yield than FP. Overall, among all the TCE treatments the RW system yields and net returns were maximum under ZTDSR+R –ZTW+R. The fastest mean infiltration rate (0.10 cm/h) was registered in ZTDSR+R –ZTW+R plots, whereas the slowest was in FP plots (0.05 cm/h). Bulk density at 15 –20-cm soil depth was least in ZTDSR+R –ZTW+R (1.70 Mg/m 3 ) and greatest in FP (1.73 Mg/m 3 ). Results from this study revealed that conventionally tilled (CT) and transplanting of rice could be successfully replaced by adoption of the profitable double ZT–RW system.
- ItemSulfur Availability Minimizes Nitrate Leaching Losses in Vulnerable Agricultural Soils(2024-05-16) Sampson Agyin-Birikorang; Cisse Boubakary; Davie M. Kadyampakeni; Raphael Adu-Gyamfi; Rachel A. Chambers; Ignatius Tindjina; Abdul-Rahman A. FuseiniDespite the critical need for nitrogen (N) in cropping systems, excessive N fertilizer application has severe environmental consequences. The synergistic interaction between sulfur (S) and N in plant nutrition could be exploited to increase N utilization, thereby maximizing N recovery and reducing losses. In a three-year study at six locations across three countries (USA, Ghana, and Mali), we evaluated the effect of S availability on N leaching losses from N fertilizer application using corn as the study crop. The study consisted of three S sources (micronized elemental sulfur [MES], untreated elemental sulfur [ES], and ammonium sulfate [AS]); five S application rates [(i) site-specific recommended S rate (SR), (ii) ¼ of the recommended S rate (25%_SR) (iii) ½ of the recommended S rate (50%_SR), (iv) ¾ of the recommended S rate (75%_SR); and (v) 1¼ of the recommended S rate (125%_SR)]; and a single N application rate (site-specific recommended N rate). Regardless of the S source, N recovery progressively increased with increasing S application rate. For the AS and MES sources, leachate nitrate concentration from the treatments with S application ≥ SR was statistically similar to that of the background concentrations, and the highest concentrations occurred with the treatment with no S application. Thus, for environmental stewardship, a critical look into S application in cropping systems is a necessity due to its synergistic interaction with N. In addition to improving productivity and enhancing efficient recovery of applied N fertilizers, S availability will minimize nitrate leaching commonly associated with application of N fertilizers.
- ItemTeff (Eragrostis Tef) Dry Matter Yield, Nutrient Uptake Partitioning, and Nitrogen Use Efficiency Indices Affected by Nitrogen Rate under Balanced Fertilization(2024-06-10) Mulugeta Demiss Belew; Upendra Singh; Job Fugice; Zachary P. Stewart; Latha NagarajanTeff [Eragrostis tef (Zucc.) Trotter] has gained high demand and popularity across the world in recent years. Data on nutrient uptake and partitioning and nitrogen use efficiency (NUE) indices of teff under balanced fertilization are scarce. A greenhouse experiment was conducted to study the effect of six different nitrogen (N) rates (0,25,50,100,150,200 mg N kg−1) on the agronomic performance of teff. These treatments were arranged in a Complete Randomized Design with four replicates. Aboveground dry matter N and phosphorus (P) uptake increased with an increasing N rate, while potassium (K) uptake increased up to 50 mg N kg−1 and then started to decline. The dry matter yield followed the order straw > grain > roots. N uptake followed the order grain > straw > roots. P uptake also showed significant (p < 0.001) differences across the plant parts and followed the order grain > straw > roots. Most of the K was taken up by straw, followed by grain and roots. N fertilization had a significant (p < 0.001) effect on grain protein, N partial factor productivity and NUE of teff. Differences in N harvest index, N recovery efficiency, N agronomic efficiency, and N agrophysiological efficiency were not statistically significant due to the N rate. Nitrogen rates of 100 mg kg1 gave an optimal NUE for teff. However, the application of 150 mg kg1 N rate resulted in the highest grain yield. Additionally, the results indicated a negative correlation between yield and NUE. In summary, our findings suggest that applying 150 mg kg N−1 to teff could be considered a beneficial nitrogen fertilization practice. This approach enhances yield, nutrient uptake, and various traits related to nutrient use efficiency, thereby elevating teff’s importance as both a food and feed crop.
- ItemInfluence of Landscape Position on Sorghum Yield Response to Different Nutrient Sources and Soil Properties in the Semi-Arid Tropical Environment(2024) Getachew Agegnehu; Beza Shewangizaw; Gizaw Desta; Shawel Asefa; Gizachew Legesse; Samuel Adissie; Ayalew Addis; Baye Ayalew; Tilahun Amede; Fayisa Olana Bulo; Mulugeta Demiss Belew; Workat Sebnie; Kassa Sisay; Habtemariam Teshome; Tesfaye Feyisa; Andre van Rooyen; Wendt John; Latha Nagarajan; Upendra Singh; Zachary P. StewartUnderstanding the response of crops to nutrient applications in undulating landscapes is imperative to improve nutrient use efficiency and crop yield. This study aimed to identify sorghum yield-limiting nutrients and characterize soil properties targeting landscape positions. The field experiments were conducted across 52 sites in four districts, covering three distinct landscape positions during the 2020 and 2022 cropping seasons. The treatments were All-blended, All- compound, All- individual, 150% of All- blended, All- blended-K, All- blended-S, All-blended-Zn, All -blended-B, recommended NP, 50% of All -blended, and control (no fertilizer). Treatment sequencing was randomized using a complete block design under foot slope (FS), mid-slope (MS), and hillslope (HS) positions. Results revealed that landscape position significantly affected the growth and yield of sorghum. Significantly higher yields were obtained from foot slopes than mid-slope and hillslope positions. Yield response to the application of nutrients significantly decreased with increasing slope. Overall, yield among all landscape positions was in the decreasing order of FS>MS>HS. The application of nutrients at different rates significantly improved sorghum total biomass and grain yield. Raising the all-blended treatment rate by 50% increased sorghum yield by 44% and 147% over the application of 50% of all nutrients and the unfertilized control treatment, respectively. Statistically significant yield differences were not observed among blended, compound, and separate applications of nutrients. The omission of K, S, Zn, and B did not show a significant variation in yield over the recommended NP fertilizer. The results of soil analysis results revealed that N and P are the most commonly deficient nutrients in sorghum-growing areas. The mean average volumetric soil moisture content ranged from 5.9-28.7% across landscape positions, with the highest at the foot slope and lowest at the hillslope position. Further research is suggested to determine economically optimum N and P rates across the three landscape positions.