There are two categories of datasets available in ALUES, land units and crop requirements.
The land units datasets are input land units with properties meant for evaluation for crop production. Two regions are available for these datasets: Marinduque, Philippines; and, Lao Cai, Vietnam. Further, these datasets are encoded into three characteristics: land or soil and terrain (LT), water and temp (for temperature). So that, for Marinduque, the following are the datasets:
MarinduqueLTMarinduqueWaterMarinduqueTempAnd for Lao Cai, Vietnam, the following are the datasets:
LaoCaiLTLaoCaiWaterLaoCaiTempSample head of the datasets are as follows:
library(ALUES)
head(MarinduqueLT)
## Lat Lon CECc pHH2O CFragm SoilTe
## 1 121.8792 13.52084 12 53 11 12
## 2 121.8875 13.52084 12 52 9 12
## 3 121.8958 13.52084 12 53 10 12
## 4 121.9375 13.52084 12 52 10 12
## 5 121.9458 13.52084 12 54 12 12
## 6 121.9542 13.52084 13 54 11 12
head(LaoCaiLT)
## SlopeD CFragm SoilDpt SoilTe CECc SumBCs pHH2O BS OC Flood
## 1 1 0 45 9 18.6 3.30 5.4 50.00 1.40 3
## 2 1 0 45 9 18.6 3.30 5.4 50.00 1.40 3
## 3 1 0 45 9 18.6 3.30 5.4 50.00 1.40 3
## 4 1 0 45 9 18.6 3.30 5.4 50.00 1.40 3
## 5 1 0 45 9 18.6 3.30 5.4 50.00 1.40 3
## 6 1 5 65 3 19.8 3.13 5.3 34.72 1.21 2
The columns of the datasets correspond to the factors or parameters measured from the land units. These parameters are used to compare to the standard values required for the target crop. The score of the comparison is referred to as the suitability score.
There are 56 crops available in ALUES, each of which encodes standard properties of the target crop. These crop datasets are further categorized into four characteristics: terrain, soil, water and temp. So that, for avocado, the datasets are encoded as
AVOCADOTerrain, AVOCADOSoil, AVOCADOWater and AVOCADOTemp. The list of crop datasets can be extracted as follows:
d <- utils::data(package = "ALUES")
alues_data <- d$results[, "Item"]
crop_data <- regmatches(alues_data, gregexpr(paste0("^[A-Z]{2,}", collapse = "|"), alues_data))
crop_data <- unique(unlist(lapply(crop_data, function(x) substr(x, 1, nchar(x)-1))))
crop_data
## [1] "ALFALFA" "AVOCADO" "BAMBOO" "BANANA" "BARLEY"
## [6] "BEANCA" "BEANS" "CABBAGE" "CARROTS" "CASHEW"
## [11] "CASSAVA" "CHICKPEA" "CINNAMON" "CITRUS" "COCOA"
## [16] "COCONUT" "COFFEEAR" "COFFEERO" "COTTON" "COWPEA"
## [21] "CUCUMBER" "GROUNDNUTS" "GUAVA" "LONGAN" "MAIZE"
## [26] "MANGO" "MILLETS" "OILPALM" "OLIVES" "ONION"
## [31] "PAPAYA" "PEACH" "PEAR" "PEA" "PEPPERGR"
## [36] "PERSIMMON" "PINEAPPLE" "PLUM" "POTATOSW" "POTATO"
## [41] "RICEBR" "RICEIW" "RICENF" "RICEUR" "RUBBER"
## [46] "SAFFLOWER" "SESAME" "SORGHUM" "SOYA" "SUGARCANE"
## [51] "SUNFLOWER" "TEA" "TOBACCO" "TOMATO" "WATERMELON"
## [56] "WHEAT"
Sample crop requirement datasets are given below:
GUAVASoil
## code s3_a s2_a s1_a s1_b s2_b s3_b wts
## 1 CFragm 55.0 35.0 15.0 <NA> <NA> <NA> <NA>
## 2 SoilDpt 30.0 50.0 100.0 <NA> <NA> <NA> <NA>
## 3 CECc 16.0 16.0 16.0 <NA> <NA> <NA> <NA>
## 4 BS 19.9 20.0 35.0 <NA> <NA> <NA> <NA>
## 5 SumBCs 1.5 1.6 2.8 <NA> <NA> <NA> <NA>
## 6 pHH2O 4.5 5.2 5.5 7.8 8 8.2 <NA>
## 7 OC 0.7 0.8 1.2 <NA> <NA> <NA> <NA>
## 8 ECedS 4.0 3.0 2.0 <NA> <NA> <NA> <NA>
## 9 ESP 25.0 20.0 15.0 <NA> <NA> <NA> <NA>
GUAVATemp
## code s3_a s2_a s1_a s1_b s2_b s3_b wts
## 1 TyAv 10 15 20 28 34 34.1 <NA>
CINNAMONTerrain
## code s3_a s2_a s1_a s1_b s2_b s3_b wts
## 1 SlopeD 6.0 4.0 2 <NA> <NA> <NA> 2
## 2 Flood 1.5 1.2 1 <NA> <NA> <NA> 1
CINNAMONWater
## code s3_a s2_a s1_a s1_b s2_b s3_b wts
## 1 WgAv <NA> <NA> 1000 2000 <NA> <NA> <NA>
## 2 WghAv <NA> <NA> 85 90 <NA> <NA> <NA>
Each datasets are well documented, so make sure to check it for details and descriptions of the parameters used.