Coffee Yield Research Articles

Prediction of arabica coffee production using artificial neural network and multiple linear regression techniques

Crop yield and its prediction are crucial in agricultural production planning. This study investigates and predicts arabica coffee yield in order to match the market demand, using artificial neural networks (ANN) and multiple linear regression (MLR). Data of six variables, including areas, productivity zones, rainfalls, relative humidity, and minimum and maximum temperature, were collected for the recent 180 months between 2004 and 2018. The predicted yield of the cherry coffee crop continuously increases each year. From the dataset, it was found that the prediction accuracy of the R2 and RMSE from ANN was 0.9524 and 0.0784 tons, respectively. The ANN model showed potential in determining the cherry coffee yields.

Tradeoffs and synergies among ecosystem services, biodiversity conservation, and food production in coffee agroforestry

Concerns over the capacity of the world’s existing agricultural land to provide food for the global population under climate change and continued biodiversity loss have set the stage for a prevailing narrative of inherent tradeoffs with agricultural production. Coffee, a major export of tropical countries, offers a unique opportunity to examine how different management practices can lead to a variety of outcomes in food security, ecosystem services, and biodiversity conservation. Our study examined this intersection to identify tradeoffs and synergies using compiled data from Puerto Rico. At the island level, we analyzed data on coffee yield and planted area under shade or sun management. At the farm level, we analyzed management variables (percent shade cover, maximum canopy height, ground cover, and food crop richness), non-provisioning ecosystem services variables (total farm carbon storage, soil organic carbon storage, coffee plant carbon biomass, and hurricane resistance and resilience), and biodiversity variables (ant, bird, and lizard richness and abundance). At the island level, we found that planted area was the most significant predictor of total production, suggesting no obvious tradeoff between production and shade management in coffee farms. At the farm level, canopy cover of shade trees was negatively correlated with ground cover and positively correlated with food crop richness, suggesting a synergy between agroforestry and subsistence food production. We detected mostly synergies associated with ecosystem services, biodiversity conservation, and agroforestry management and no tradeoffs among ecosystem service and biodiversity parameters. Shade canopy cover significantly increased total carbon storage, coffee plant biomass, hurricane resistance, and bird species richness. Shade canopy height had a similar positive effect on total farm carbon storage while food crop richness had a positive effect on farm resilience following Hurricane Maria. Ground cover was positively associated with soil carbon storage and pest-controlling lizard abundance. Tradeoffs related to agroforestry management included an inverse relationship between ground cover and hurricane resistance and more dominance of an invasive ant species in farms with higher shade canopies. We discuss the implications of practicing agroforestry principles in this smallholder coffee system and highlight opportunities to contribute to more diversified food production systems that support biodiversity and ecosystem services.

Foliar-applied silicon may enhance fruit ripening and increase yield and nitrogen use efficiency of Arabica coffee

Nitrogen (N) is an essential element that is required in the highest amounts by the arabica coffee (Coffea arabica L.) trees. The efficiency of N fertilization in coffee could be improved by the application of silicon (Si). Thus, the objective of this study was to evaluate the effect of foliar application of soluble Si and N fertilizer on nutrition, vegetative growth, fruit ripening, bean yield, and N-use efficiency of Arabica coffee. The experiment took place from 2013 to 2017 on an Arabica coffee plantation established on a sandy clay loam Acrisol of southeastern Brazil. It was arranged in a randomized complete block design with four replications. Treatments consisted of the combination of the presence and absence of foliar application of Si with four N rates (0–300 kg N ha−1 year−1). The foliar application of Si was performed by spraying stabilized silicic acid two times per growing season (Nov. and Feb.). The source of N used was ammonium nitrate (32% N), and it was split four times (Oct.–Feb.) each year. Nitrogen fertilization reduced the stoichiometric ratios among most other nutrients and N in coffee leaves, especially by increasing plant growth and leaf N concentration. In addition, it contributed to the maintenance of plant leafiness, besides increasing the percentage of ripe fruits and coffee bean yield. Despite having only little effect on the concentration and stoichiometry of nutrients in leaves and on plant growth, Si application increased the bean yield of coffee. This was particularly so under the highest N rates, as well as the agronomic efficiency of N applied to the crop in some conditions. Silicon also reduced the percentage of dry fruits in 2017 and increased the percentage of ripe fruits (2015 and 2017). In conclusion, spraying coffee with Si in form of stabilized silicic acid potentially improves the N-use efficiency in the crop.

Integrating effects of neighbor interactions for pollination and abiotic resources on coffee yield in a multi‐strata agroforest

AbstractAnimal‐pollinated plants interact with neighbors for both abiotic resources and pollination, with consequences for reproduction and yield. Yet few studies have compared the relative magnitude of these effects, particularly in agroecosystems. In vertically stratified communities, such as agroforests, neighbor effects may be stratum‐dependent. Understanding the net effects of neighbors on crop yield is important for managing multifunctional agroecosystems to simultaneously support production and biodiversity. This study evaluated the effects of neighboring plants on pollen deposition, fertilization, and yield in Coffea arabica in a shaded organic coffee farm with high non‐crop plant abundance and diversity in Chiapas, Mexico. We assessed the impact of (1) floral resources at three vertical strata (herbs, coffee bushes, and canopy trees) on stigma pollen load (a measure of interaction for pollination), and (2) floral density and canopy cover (proxies for competition for abiotic resources) on yield (final fruit set and per‐fruit weight), using structural equation modeling to evaluate the relative effect of each interaction type. Coffee competed for pollination with neighbors (conspecifics and heterospecifics) across strata. Pollen load influenced final fruit set, but the effect of neighbor competition for pollination was weaker than effects mediated by interactions for abiotic resources. Effects of interactions for abiotic resources were heterogeneous across strata, with negligible effects of herb‐layer or coffee flower density but net positive effects of canopy trees on final fruit set. Overall effects of neighbors on coffee yield were weak, suggesting that coffee agroecosystems can be managed to maintain high plant density and diversity without sacrificing yield.Abstract in Spanish is available with online material.

Genetic variability for vigor and yield of robusta coffee (Coffea canephora) clones in Ghana

Effectiveness of plant improvement programs, especially in perennial crops like coffee, may be improved by knowing the level of genetic variation which exist within a breeding population coupled with the knowledge of estimates of genetic parameters for key agronomic traits. Thus, this study was conducted to evaluate C. canephora clones for growth (stem diameter, number of laterals and span) and yield traits; estimate genetic parameters of these traits; and determine the phenotypic and genetic associations between these traits to guide future crop improvement efforts. The productivity of 56 coffee clones was assessed from 2012 to 2020 in a clonal experiment planted in a randomized complete block design with three replicates. Each plot consisted of eight plants spaced at 2 × 3 m at the Cocoa Research Institute of Ghana. There were significant (p < 0.001) differences among clones for all the traits assessed. Broad sense heritability was low-to-moderate for all the traits evaluated with the highest (0.34) observed for cumulative yield (CY). Cumulative yield was genetically correlated (p < 0.001) with span and number of laterals (NOL). For the growth traits, NOL was the most strongly associated with CY (rg = 0.49, p < 0.001). The results revealed that selection based on early years’ yield (MY1) could be as effective as selection based on CY (rg = 0.87, p < 0.001). Our findings indicate that there is significant genetic variation among the test clones for the parameters assessed and presents a good opportunity for future variety development.

Ecosystem services from coffee agroforestry in Central America: estimation using the CAF2021 model

The goal of sustainable coffee production requires multiple functions from agroforestry systems. Many are difficult to quantify and data are lacking, hampering the choice of shade tree species and agronomic management. Process-based modelling may help quantify ecosystem services and disservices. We introduce and apply coffee agroforestry model CAF2021 (https://doi.org/10.5281/zenodo.5862195). The model allows for complex systems with up to three shade tree species. It simulates coffee yield, timber and fruit production by shade trees, soil loss in erosion, C-sequestration, N-fixation, -emission and -leaching. To calibrate the model, we used multivariate data from 32 different treatments applied in two long-term coffee agroforestry experiments in Costa Rica and Nicaragua. Without any further calibration, the model was then applied to agroforestry systems on 89 farms in Costa Rica and 79 in Guatemala where yields had been reported previously in farmer interviews. Despite wide variation in environmental and agronomic conditions, the model explained 36% of yield variation in Costa Rica but only 15% in Guatemala. Model analysis quantified trade-offs between yield and other ecosystem services as a function of fertilisation and shading.

Partnership for Sustainable Coffee Certification: Linking Up Smallholder Farmers to Global Coffee Market

This study examines the impacts of partnerships for sustainability certifications in coffee value chains on farm income in Lampung Province, Sumatra-Indonesia. We conducted farm-household surveys, interviewing 171 samples in West Lampung and Tanggamus Districts, consisting of 98 farmers joining partnership and 73 farmers not joining. A probit model is used to determine decisions to join the partnership; ordinary least square (OLS) is used to analyze the determinants of farm income; and Heckman selection-correction model is used to reduce the selection bias in partnership participation. We find some selection in partnerships for sustainability certifications, driven by the age and education of household head, land holding size of coffee farm and the proximity to rural cooperatives-KUBE. The partnership farmers earn higher farm income than those not joining, due to a higher proportion of productive family members. After employing the treatment-effect model, we find that the partnership for sustainability certifications raises farm income, mostly due to higher coffee yield and farm-gate prices. These results reveal the need for policies to support the establishment and encouragement of partnerships for sustainability certifications. The internal control system (ICS) initiated by coffee corporations in implementing the sustainability certifications have improved the trust level between smallholders and global corporations.

The role of machine learning on Arabica coffee crop yield based on remote sensing and mineral nutrition monitoring

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 −1 in 6/15/2005 for yield classification in the first node and this threshold obtained is consistent with the available literature associated with high coffee yields between 3.6 and 4.0 g kg −1 . • Machine learning with big data enabled to predict coffee yield variation in the field. • Random forest and rpart1SE modelling provided insights for crop yield management. • Leaf mineral nutrition must be considered for coffee yield management in the field.

Review on Heterosis and Combining Ability Study for Yield and Morphological Characters of Coffee (Coffea arabica L) in Ethiopia

Ethiopia is both the center of origin and diversification of Coffee arabica. Despite the existence of high genetic diversity in coffee population that provides immense opportunities for improvement program, shortage of improved varieties (pure line and hybrid varieties) is the major one. It is obvious that research work carried out so far on coffee genetics and breeding was not adequate to address these diverse agro-ecologies of the country. Heterosis and combining ability studies are some of the basic breeding tools to address such problems. Some studies had been focused on assessment of heterosis and combining ability analysis for yield and morphological characters of coffee in Ethiopia and the presence of heterosis was reported in crosses of selected indigenous C. arabica L. varieties in Ethiopia under different set of studies mainly due to presence of diverse parental lines. These results clearly suggested that the possibility to bring significant coffee improvement through heterosis and combining ability analysis. Therefore, continuous crossing program should be required to acquire many more cross combinations for intensive and extensive evaluation to develop better performing and high yielding hybrids for Ethiopian origin coffee. Keywords: Coffee Arabica, morphological traits, yield, Heterosis and combining ability DOI: 10.7176/JEES/12-7-02 Publication date: July 31 st 2022

Optimization of water use in Coffea arabica L. grown under different agronomic practices

Lower water availability due to climate change has dramatically affected coffee yields and quality. Characteristics related to plants and soil can be explored to obtain more productive and sustainable coffee production under adverse crop conditions. To this end, the objective of this study was to evaluate the potential for using different agronomic practices to optimize water use in coffee plants and to mitigate the effects of lower water availability to the crop. In the plots, three soil management systems (polyethylene film, brachiaria and bare soil) were used. In the subplots, two types of fertilizers were used (conventional and controlled-release fertilizer). Five soil conditioners (coffee husk, gypsum, water-retaining polymer, organic compost, and the control) were distributed throughout the sub-subplots. The plant growth, soil moisture, leaf physiology and anatomy, and soil chemical properties of coffee plants were analysed. The management of the soil cover using polyethylene film or brachiaria stood out as agronomic practices that can be combined with coffee husk applications to enable the better use of water by coffee plants and to favour soil conditioning. Controlled-release fertilizer and gypsum allowed for improvements in the anatomical and physiological characteristics of the plants. The use of organic compost favoured greater water availability; however, it caused losses in terms of coffee growth and physiological parameters due to nutritional imbalance. Therefore, based on results, the use of polyethylene film, brachiaria, controlled-release fertilizer, coffee husks, and gypsum are potential agronomic practices for optimizing water use and mitigating the effects of water deficit in coffee plants

Modeling age and yield dynamics in Coffea arabica pruning systems

CONTEXTThe maintenance of rejuvenated, productive plant tissue through regular and frequent pruning is essential to sustain high and stable coffee yields. Different coffee pruning systems have been described by means of well-written descriptions, and ingenious drawings and graphs. The mathematical representation of coffee pruning systems has never been attempted. Until now. OBJECTIVETo develop a mathematical modeling approach capable of describing plant tissue age and coffee bean yield dynamics for any coffee pruning system. RESULTS AND CONCLUSIONSIn this paper, we develop mathematical models for simple (Nicaragua) and complex (El Salvador) coffee pruning system by using a special type of additive age-projection matrix, clock arithmetic, step functions, and coffee yield-age functions developed using expert knowledge. Simulations were run to answer three fundamental crop management questions: 1) how many years is the best pruning cycle, 2) when (at what age?) to start pruning, and 3) how different yield-age functions influence decisions on the best pruning cycle and age at first stumping?. SIGNIFICANCECoffee pruning models can help coffee agronomists to design and test innovative pruning practices quickly, efficiently, and cheaply. Pruning models can be coupled with financial data to improve decision making in crop management. The mathematical approach used for Arabica coffee pruning systems is equally applicable to Robusta coffee.

Early Prediction of Coffee Yield in the Central Highlands of Vietnam Using a Statistical Approach and Satellite Remote Sensing Vegetation Biophysical Variables

Given the present climate change context, accurate and timely coffee yield prediction is critical to all farmers who work in the coffee industry worldwide. The aim of this study is to develop and assess a coffee yield forecasting method at the regional scale in Dak Lak province in the central highlands of Vietnam using the Crop Growth Monitoring System Statistical Tool (CGMSstatTool—CST) software and vegetation biophysical variables (NDVI, LAI, and FAPAR) derived from satellite remote sensing (SPOT-VEGETATION and PROBA-V). There has been no research to date applying this approach to this specific crop, which is the main contribution of this study. The findings of this research reveal that the elaboration of multiple linear regression models based on a combination of information from satellite-derived vegetation biophysical variables (LAI, NDVI, and FAPAR) corresponding to the first six months of the years 2000–2019 resulted in coffee yield forecast models presenting satisfactory accuracy (Adj.R2 = 64 to 69%, RMSEp = 0.155 to 0.158 ton/ha and MAPE = 3.9 to 4.7%). These results demonstrate that the CST may efficiently predict coffee yields on a regional scale by using only satellite-derived vegetation biophysical variables. This study findings are likely to aid local governments and decision makers in precisely forecasting coffee production early and promptly, as well as in recommending relevant local agricultural policies.

Statistical Analysis of the Weather Impact on Robusta Coffee Yield in Vietnam

Weather and climate strongly impact coffee; however, few studies have measured this impact on robusta coffee yield. This is because the yield record is not long enough, and/or the data are only available at a local farm level. A data-driven approach is developed here to 1) identify how sensitive Vietnamese robusta coffee is to weather on district and provincial levels, 2) during which key moments weather is most influential for yield, and 3) how long before harvest, yield could potentially be forecasted. Robusta coffee yield time series were available from 2000 to 2018 for the Central Highlands, where 40% of global robusta coffee is produced. Multiple linear regression has been used to assess the effect of weather on coffee yield, with regularization techniques such as PCA and leave-one-out to avoid over-fitting the regression models. The data suggest that robusta coffee in Vietnam is most sensitive to two key moments: a prolonged rainy season of the previous year favoring vegetative growth, thereby increasing the potential yield (i.e., number of fruiting nodes), while low rainfall during bean formation decreases yield. Depending on location, these moments could be used to forecast the yield anomaly with 3–6 months’ anticipation. The sensitivity of yield anomalies to weather varied substantially between provinces and even districts. In Dak Lak and some Lam Dong districts, weather explained up to 36% of the robusta coffee yield anomalies variation, while low sensitivities were identified in Dak Nong and Gia Lai districts. Our statistical model can be used as a seasonal forecasting tool for the management of coffee production. It can also be applied to climate change studies, i.e., using this statistical model in climate simulations to see the tendency of coffee in the following decades.

Shade effects on yield across different Coffea arabica cultivars — how much is too much? A meta-analysis

The coffee research community has maintained a long ongoing debate regarding the implications of shade trees in coffee production. Historically, there has been contrasting results and opinions on this matter, thus recommendations for the use of shade (namely in coffee agroforestry systems) are often deemed controversial, particularly due to potential yield declines and farmers’ income. This study is one of the first demonstrating how several Coffea arabica cultivars respond differently to shade with respect to yield. By standardising more than 200 coffee yield data from various in-field trials, we assembled the so-called “Ristretto” data pool, a one of a kind, open-source dataset, consolidating decades of coffee yield data under shaded systems. With this standardised dataset, our meta-analysis demonstrated significant genotypic heterogeneity in response to shade, showing neutral, inverted U-shaped and decreasing trends between yield and shade cover amongst 18 different cultivars. These findings encourage the examination of C. arabica at the cultivar level when assessing suitability for agroforestry systems. Comparison of productivity is also encouraged across a range of low to moderate shade levels (10–40%), in order to help elucidate potential unknown optimal shade levels for coffee production.

KEBIJAKAN BISNIS DALAM PENINGKATAN HASIL PANEN PETANI KOPI DI KABUPATEN BENER MERIAH

The issue is a lack of care for the coffee plant, which makes it easier for diseases and pests to spread and results in low harvests. In order for the community to experience progress, independence, and welfare in a setting of lasting social justice, the community must be prepared, and institutions within the community must be strengthened. Knowing in advance what coffee farmers require will allow the extension agency to create a collaborative program with farmer organizations as part of the Agriculture Service's empowerment approach to boost coffee yields. Developing the skills of communities that grow coffee and are part of farmer organizations through training. It is essential to take proper care of the plant, use high-quality seeds, get enough organic and inorganic fertilizer, and apply pesticides to keep out pests in order to improve the output of high-quality coffee.

Biophysical drivers of yield gaps and ecosystem services across different coffee-based agroforestry management types: A global meta-analysis

The productivity of agroforestry systems (AFSs) and the provisioning of associated ecosystem services (ESs) are threatened by increasing cropping intensification and climate change. Compared to full-sun coffee, maintaining shade cover might protect against climate variability, forest degradation, and pests/diseases attack. However, there may be trade-offs between yields and ESs. While the impacts of shade have been reviewed, a global synthesis to understand how shade trees and a range of practices and biophysical factors contribute to yield gaps and ESs across management types is lacking. This research aims at integrating quantitative data on management practices (shade cover percentage, tree/coffee plant densities, and nutrient inputs), coffee/tree characteristics, soil properties, topographic attributes and climate, in order to compare the responses of coffee yields, biodiversity and ES supply across management types. We conducted a meta-analysis with a total of 142 papers that fulfilled the inclusion criteria and analyzed the individual and combined effects of these factors. The results show that factors such as shade cover and tree/plant densities affected more the yields than climatic and biotic factors. AFSs under moderate shade cover levels (35–50%), with tree densities between 100 and 250 trees ha−1, at low altitudes, and with steeper slopes provided as much yields as full-sun systems (4.1 ± 2.88 tons ha−1 yr−1). While increased shade cover (>51%) decreased yields, the results also show that more diversified AFSs can support biodiversity conservation and provide ESs such as stored carbon, infiltration, pollination, and water runoff. The generalized linear models (GLMs) analyses showed that coffee yield variations are highly context-dependent and factors such as the incidence of pest/leaf rust, altitude, soil quality, available water, and biodiversity may play an important role. The novelty of this research is that the effect of shade, coffee plants, and input management practices is taken into account, along with the effects of a range of site-specific biophysical factors; along with the application of a case study to test robustness of the meta-analysis. This study provides an understanding of the effects of management type gradients on coffee yield and whether the low yields in AFSs compared to conventional coffee monocultures, are compensated by the provisioning of ESs.

Mapping coffee yield with computer vision

Mapping coffee yield with computer vision

Assessment of spatio-temporal patterns of coffee wilt disease, constraints on coffee production and its management practices in Berbere district, Bale Zone, southeastern Ethiopia

Investigation of coffee wilt disease (CWD) caused by Gibberella xylarioides was made to determine the spatio-temporal pattern, socio-economic challenges and management practices in Berbere district between 2017 and 2018. A field and household surveys were employed for the study. The incidence and severity of CWD were varied among the study villages (p < 0.05), but not between dry and wet seasons (p > 0.05). The variation in the disease severity was due to variations in the disease incidence among study villages, and in dry or wet season. The mean yield of coffee was higher before 2009 than after 2008 (p < 0.0001). Coffee wilt disease caused largely economic losses and shifting coffee cultivation; found frequently on older and densely planted coffee. Replacing with new seedlings and weeding were used largely for CWD management. There is an increasing intensity of CWD in the district, suggesting an integrated disease management option.

Obtaining and Validating High-Density Coffee Yield Data

Coffee producers are ever more interested in understanding the dynamics of coffee’s spatial and temporal variability. However, it is necessary to obtain high-density yield data for decision-making. The objective of this study is to evaluate the quality of yield data obtained through a yield monitor onboard a coffee harvester, as well as to evaluate the potential of the data collected over three harvests. The yield monitor validation data showed a high correlation (above R2 0.968) when compared with the data obtained by a wagon instrumented with load cells. It was also possible to obtain yield maps for three consecutive seasons, allowing the identification of their internal variability, as well as classifying regions that show alternating yield patterns between years as the expression of the biennial yield behavior manifested inside and along the field, in addition to the spatial variability. This result indicates that, in addition to knowing the spatial yield variability, the biennial variance information must also be considered in the strategies for site-specific management. Regions that presented high yield variance should be alternated according to the productive year (high and low yield) and not only in consideration of their yield variability as on the regions with more stable yield behavior over time. The use of yield data can help the producer make more assertive decisions for crop and farm management.

The Dark Side of Shade: How Microclimates Drive the Epidemiological Mechanisms of Coffee Berry Disease.

Coffee berry disease (CBD) can cause significant coffee yield losses along with major income losses for African smallholders. Although these farmers cannot afford to purchase pesticides to control the disease, agroecological solutions have rarely been investigated, and how epidemiological mechanisms are linked to the environment of the coffee tree and the plot remains unclear. Agroforestry systems are a promising agroecological option, but the effect of shade on CBD regulation is the subject of debate, and the use of plant species diversity remains uncertain. Here, we address how shade affects epidemiological mechanisms by modifying the microclimate. For this purpose, we developed a mechanistic susceptible-exposed-infectious-removed model and used a Bayesian framework to infer the epidemiological parameters against microclimatic covariates. We show that shade has opposing effects on different epidemiological mechanisms. Specifically, shade can limit disease dynamics by reducing disease transmission while simultaneously promoting disease dynamics by reducing the latent period of the pathogen. However, in full sun, efficient disease transmission compensates for long latent periods. As a result, the balances between microclimatic variables can counterbalance the epidemiological rates, which can dramatically alter the fate of epidemics in shade versus full sun conditions. We propose research avenues to help design cost- and environmentally effective management strategies for CBD that are notably based on the functional traits of shade trees that could hamper CBD dispersal.