3.1. Status of the Banana Trees Based on the Aerial Photos-Derived Spectral Indices
The NDVI map showed values ranging from -0.17 to 0.80. Although these values are unitless, the negative values indicate that water bodies exist around the plantation. In contrast, values ranging from 0 to 0.75 indicate bare soil and sparse and dense vegetation (
Figure 3). NDVI values for Ambon, Kapas and Kepok ranged from 0.21 to 0.80, 0.42 to 0.73 and 0.05 to 0.74, respectively (
Table 2). Additionally, the NDVI values seemed to be able to distinguish the type of disease that infected the bananas. The range of NDVI values for Fusarium were lower than those for BDB in Kepok and Ambon bananas. However, the highest (maximum) NDVI values did not always correspond to healthy bananas. All cultivars also had a good maximum NDVI value, whether they were infected by Fusarium or by BDB (
Table 2). Therefore, we concluded that NDVI has limitations when it comes to determining the type of disease affecting a banana tree.
Unlike the NDVI map, the NDWI map showed that the level of soil moisture or available water content in the soil ranged from -0.32 to 0.02. This range explains the near real-time condition of soil below the canopy, and bare soil areas are driest (
Figure 4). In an ideal situation, NDWI will show values ranging from -1 (driest) to 1 (wettest). Fusarium and BDB affecting Ambon and Kapas bananas had higher NDWI values than those affecting Kepok. BDB was also found in the driest soil (
Table 2). Similar to those of NDVI, MCARI values are also unitless, and their uncertainty in investigating banana diseases becomes the principal issue. However, the lowest MCARI value indicates the lowest capability for photosynthesis. The MCARI values ranged from -33.352 to 26.083 and describe the variation in photosynthesis for all plants that appear in the aerial photos (
Figure 4). This is likely only suitable for studying Fusarium and BDB in Ambon and Kepok bananas with the lowest MCARI values (
Table 2). A better interpretation was obtained using soil pH for all infected bananas. Fusarium and BDB are primarily found in soil with a pH lower than 6.00 (
Table 2).
All derived vegetation indices maps and their estimated values created uncertainties. However, we thought a different perspective might have the potential to give new insight. Each banana cultivar observed in the field was supported by a longitude and latitude, which also correspond to the vegetation-soil indices values shown in
Table 2. Therefore, once we sorted it from the lowest to the highest, we understood how the relative spatial distribution of Fusarium and BDB can be related to the environmental condition based on vegetation- and soil-derived indices (
Figure 5a-d).
This explanation is regarding the dynamic range of NDVI values rather than the sample size. Next, we considered using the extracted NDVI values to determine the number of banana trees infected by BDB and Fusarium, as well as the healthy bananas. Once the median value of NDVI values was set at 0.50, the number of healthy bananas increased along with the NDVI values. In contrast, when the NDVI values decreased, the number of infected trees increased. However, the affected banana trees were still found to have high NDVI values. This is better than many affected banana trees which had decreased NDVI values (
Figure 5a)
Unfortunately, the same procedure failed when applied to the NDWI values. Since the soil condition during the time of this study was the driest although it was not drought season, we found that when the NDWI values decreased, the number of affected trees exceeded that of healthy trees. On the other hand, soil moisture is not our focus. We assumed that the banana trees were already affected by BDB and Fusarium a day or more before our observation. However, Clayton, Oritsejafor, and Yan & Nelson were confident in explaining that the survival of the fungus may decrease with increased soil moisture [
14,
15,
16]. According to the present study’s findings, banana trees affected by BDB and Fusarium increased when soil moisture (expressed by NDWI) decreased (
Figure 5b). Moreover, NDWI explains how remote sensing can measure the actual water content absorbed by the soil in any condition [
12,
48].
Similar to NDVI, MCARI values ranged from -35 to 26, and we divided them into two groups: positive and negative. This is helpful for explaining why more healthy banana trees had positive (highest) values compared to negative (lowest) values. Once NDVI rises, it is likely to be followed by increasing MCARI values. Besides, lower NDVI values mean banana trees may become unhealthy and thus have decreased photosynthetic capabilities (
Figure 5c). For instance, a banana tree may have dried leaves due to drought. A study found that when a plant absorbs limited water, its leaves will slowly get decoloured and dry [
49]. At this stage, hopefully, there is a possibility of making a connection between NDVI, MCARI, NDWI and soil pH, as well as the critical values used to identify the banana trees affected by BDB and Fusarium.
The soil pH map showed pH values ranging from 4.83 to 6.73. The soil in the study area was situated in the acidic-to-almost-neutral range. The optimum soil pH for banana growth ranges from 5.8 to 6.5 [
50,
51]. Within this range, banana trees can grow well without worries that they may not be receiving adequate minerals from the soil. In a low soil pH (< 5) there is often associated low concentrations of base cations and nutrients such as Ca
2+ and Mg
2+ or high contents of aluminium and manganese [
52,
53,
54]. In this study, some areas of the banana plantation had a lower soil pH (<5), which means the soil there has increased the amounts of aluminium and manganese. However, the samples of the soil where infected and healthy banana trees grew had pH ranging from 5.56 to 6.65. According to Orr & Nelson [
55], Fusarium generally has an inversely proportional relationship with soil pH and will only grow well when the soil pH is lower. This explains the situation we observed on the banana plantation (
Figure 5d). The number of healthy banana trees were more in places where the soil pH was high. This is similar to what Segura et al. [
56] found, taking the Gros Michel bananas (Musa AAA) as samples. Their study found that with an increase in soil pH, a reduction in the incidence of Fusarium wilt occurred in almost all cases. This is why the number of healthy bananas increased and that of affected bananas reduced with a high soil pH. Unfortunately, Fusarium can still be found whether the soil pH is high or close to neutral [
17].
The effort of UAV's derived soil information represented by the NDWI and soil pH and vegetation information represented by MCARI and NDWI linked together as the main parameters to explain the existence of BDB and Fusarium in plantation scale (
Figure 6). It is surprising that all parameters mostly had a moderate relationship. First was the lowest to the highest coefficient of determination (R
2), 0.47, -0.65 and -0.68 for soil pH against NDVI, NDWI and MCARI, respectively. The soil pH can explain the condition of banana trees at 47% accuracy. A moderate positive correlation was observed and describes the number of healthiest bananas increasing while the NDVI values move highest (
Figure 4a). The soil pH showed a moderate negative relationship (65%) with NDWI in terms of describing the banana diseases. This relationship is consistent with the finding that a decrease in NDWI values will be followed by an increase in the number of affected trees. A slightly higher negative correlation was observed between soil pH and MCARI. It reached 68% to use the relationship of soil pH and MCARI while explaining the BDB and Fusarium. For more detail on all the possible relationships between the indices, please see the pairwise correlation matrice in
Figure 5.
All the results were satisfactory since the UAV-derived spectral indices (Soil pH, NDVI, NDWI and MCARI) all showed a moderate relationship (
Figure 5) and the relationship between these spectral indices and the number of banana trees affected by BDB and Fusarium was qualitative (
Figure 4a–d). Regardless of this result, more attention needs to be paid to the unknown characteristics of the number of unhealthy and healthy banana trees in any condition explained by all derived spectral indices (Soil pH, NDVI, NDWI and MCARI). This might create an overlap and lead to difficulties determining where the clustered area of healthy banana trees and those affected by BDB and Fusarium is simultaneous. The overlapping situation shown in the paired scatterplot adequately explains how these difficulties arise.
The scatterplot in
Figure 7 shows the pairing of soil pH with MCARI, NDWI and NDVI in the first column. Here, the scatterplot of soil pH values and NDVI corresponding to disease types of the group of banana trees affected by Fusarium has a probability in the soil pH values below 6.0, while BDB below 6.50 is the same as with the healthy groups of bananas. These values correspond to NDVI values lower than 0.6 and have a probability to yield unhealthy banana trees due to infection by BDB and Fusarium. The area of intersection between these three groups of bananas is slightly challenging to classify. Unfortunately, other scatterplots of soil pH against MCARI and NDWI showed a similar pattern (
Figure 7). This situation needed to be handled in a sophisticated manner. Therefore, the distribution of BDB-infected, Fusarium-infected, and healthy banana trees was appropriately mapped. Similar to the first column, the scatterplot in the second to fourth columns had random patterns, while that between NDWI and MCARI did not and showed that healthy banana trees are likely separated from unhealthy banana trees.
3.2. The Distribution of BDB and FUSARIUM Wilt Based on Aerial Photos-Derived Spectral Indices
A distribution map of affected and healthy banana trees derived using the RF algorithm showed a dominance of Fusarium followed by BDB; healthy banana trees were the least dominant (
Figure 8). From this map, it is hard to say whether the entire banana plantation is already affected. However, since banana trees do not entirely planted in this area, and these two diseases are significant factors causing a decline in banana production, mitigating and limiting BDB and Fusarium distribution must be a priority. As suggested by Thi et al. [
58], Fusarium wilt not only impacts the overall yield during the time of infection but also affects the land used for banana cultivation for the next 20 years. In addition, all affected banana trees may have to be removed to solve the problem [
59,
60]. However, Fusarium spores will remain in the soil, and as a result, reinfection of new banana accessions in the same area is very likely in the absence of complete soil disinfection [
61].
Unfortunately, this study's RF and available dataset can neither predict when BDB and Fusarium first attacked the banana trees nor can it detect the level of affectation by BDB and Fusarium. These two diseases already affected all the mature banana trees. Using UAV-derived spectral indices—NDVI, MCRI, NDWI and soil pH—we satisfactorily determined the distribution of BDB and Fusarium. As the study by Zhang et al. [
28] stated, using derived red edge band spectral indices can also yield similar information. Here, MCARI has a critical role in determining whether the banana trees are healthy or affected. The Gini index values had the highest score at about 0.35 (35%), while NDWI, NDVI and soil pH were 0.28, 0.22 and 0.15, respectively (
Table 3). Along with this result, the overall accuracy for distribution classification reached 100% based on the RF and spectral indices used for 5 hectares (
Table 4).